Burns and Grove’s the Practice of Nursing Research 9th Edition Test Bank by Ace Test Banks

Burns and Grove’s the Practice of Nursing Research 9th Edition

By Jennifer R. Gray, Susan K. Grove

Chapter 01: Discovering the World of Nursing Research Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. Nurses with a bachelor’s degree in nursing can participate in the implementation of research

into practice. This means that the BSN nurse: a. develops evidence-based guidelines. b. designs research studies on which protocols may be based. c. evaluates and revises evidence-based protocols. d. reads and critically appraises existing studies. ANS: D

Nurses with a Bachelor of Science in Nursing (BSN) degree have knowledge of the research process and skills in reading and critically appraising studies. They use the best research evidence in practice with guidance. Nurses with a BSN also assist with problem identification and data collection. Nurses with a Master of Science in Nursing (MSN) critically appraise and synthesize findings from studies to revise or develop protocols, algorithms, or policies for use in practice. Nurses with a Doctor of Nursing Practice (DNP) develop, implement, and evaluate evidence-based guidelines. Nurses with a Doctor of Philosophy (PhD) assume a major role in conducting research. DIF: Cognitive Level: Analysis 2. A study is designed to test the idea of providing companion dogs to elders in a major hospital,

in order to determine the effect upon the elders’ level of orientation. This type of study can do which of the following? a. Control b. Describe c. Explain d. Predict ANS: A

Control is the ability to manipulate the situation to produce the desired outcome. Description involves observing and documenting nursing phenomena, providing a snapshot of reality. Explanation clarifies the relationships among concepts and variables with the goal of understanding how they work with each other. Prediction involves estimating the probability of a specific outcome in a given situation. DIF: Cognitive Level: Application 3. A researcher wants to know whether children with autism who are hospitalized in a pediatric

ward will require more hours of nursing care than the average child, when the parents or caregivers are not present. What type of research outcome does this provide? a. Control b. Description c. Explanation d. Prediction ANS: D

Prediction involves estimating the probability of a specific outcome in a given situation. Control is the ability to manipulate the situation to produce the desired outcome. Description involves observing and documenting nursing phenomena, providing a snapshot of reality. Explanation clarifies the relationships among concepts and variables with the goal of understanding how they work with each other. DIF: Cognitive Level: Application 4. Despite the presence of an intraventricular drain, the intracranial pressure of a patient in

neurological intensive care remains increased. The nurse recalibrates the machine, makes sure the monitor is on the same level as the drain, checks all connections, and then notifies the physician, who comes to the unit and inserts a new drain. What type of reasoning or thinking prompts the nurse to recalibrate, assure proper placement, and check connections? a. Abstract thinking b. Concrete thinking c. Logical reasoning d. Dialectical reasoning ANS: C

Logical reasoning is used to dissect components of a situation or conclusion, examine each carefully, and analyze relationships among the parts. Abstract thinking is oriented toward the development of an idea without application to, or association with, a particular instance. Concrete thinking is oriented toward and limited by tangible things or by events that are observed and experienced in reality. Dialectical reasoning involves looking at situations in a holistic way. DIF: Cognitive Level: Application 5. A nurse with considerable clinical expertise develops a policy for managing agitated patients

in the Emergency Department. The resultant policy emanates from: a. abstract thinking. b. concrete thinking. c. operational reasoning. d. dialectical reasoning. ANS: A

Abstract thinking is oriented toward the development of an idea without application to, or association with, a particular instance. Concrete thinking is oriented toward and limited by tangible things or by events that are observed and experienced in reality. Operational reasoning is the identification of and discrimination among many alternatives and viewpoints. Dialectical reasoning involves looking at situations in a holistic way. DIF: Cognitive Level: Application 6. A nurse with considerable clinical expertise develops a policy for managing agitated patients

in the Emergency Department. The type of reasoning the nurse uses to do this is: a. problematic reasoning. b. operational reasoning. c. collaborative reasoning. d. inductive reasoning.

ANS: D

Inductive reasoning involves reasoning that moves from the specific to the general, whereby particular instances are observed and then combined into a larger whole or general statement. Problematic reasoning involves: (1) identifying a problem and factors influencing it, (2) selecting solutions to the problem, and (3) resolving the problem. Operational reasoning involves the identification of and discrimination among many alternatives and viewpoints. Collaborative reasoning occurs when individuals with different perspectives “reason together” to develop a coordinated plan of action. DIF: Cognitive Level: Synthesis 7. What is the best explanation of the type of intuition that forms a legitimate source of

knowledge in nursing? a. It is the result of recognizing patterns in a way that allows rapid conclusions. b. It is based on a gift from the universe and should be honored when it arrives. c. It is never inaccurate. d. It is the process of examining and critiquing one’s thoughts. ANS: A

Intuition is understanding without rationale. Intuition is described as pattern recognition, seeing similarities and dissimilarities of a situation and seeing the whole in a way that allows rapid conclusions. Because intuition is a type of knowing that seems to come unbidden, it may also be described as a guy feeling, hunch, or sixth sense. Intuition cannot be explained scientifically, therefore many people discount it or are uncomfortable talking about it. Expert nurses are more likely to experience intuition, especially when they connect with their patients and are open to their feelings. DIF: Cognitive Level: Application 8. Why is operational reasoning necessary for research? a. Abstract concepts are of no use to nursing. b. Standard interventions are obtained from operational reasoning. c. It allows the researcher to devise ways to measure the concepts studied. d. It facilitates the researcher’s rapport with families. ANS: C

Operational reasoning involves the identification of and discrimination among many alternatives and viewpoints. It focuses on the process (debating alternatives) rather than on the resolution. Nurses use operational reasoning to develop realistic, measurable health goals. In research, operationalizing a treatment or intervention to implement, comparing measurement methods, and debating the appropriate data analysis techniques to use in a study require operational thought. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. Realistically, what might be done in a situation in which a nurse does not know the

appropriate way to use a new ultrasonic bladder scanner (a noninvasive, painless procedure) but has a new order at 2 a.m. to perform a scan? (Select all that apply.)

a. b. c. d. e. f.

Refuse to carry out the order. Ask a coworker who has used the equipment. Access the instructions on the company’s Internet site. Try to scan the bladder and decide if the value obtained makes sense. Notify the manager that a formal inservice is needed. Read the instruction booklet.

ANS: B, C, D, F

The nurse can seek out a coworker (an authority) who has expertise with the equipment. The company’s Internet site, or instruction booklet, provides a form of education on the skill. Trial and error is an approach with unknown outcomes that is used in a situation of uncertainty, when other sources of knowledge are unavailable. The profession evolved through a great deal of trial and error before knowledge of effective practices was codified in textbooks and journals. The trial-and-error way of acquiring knowledge can be time-consuming, because multiple interventions might be implemented before one is found to be effective. Refusing to carry out the order or asking for a formal in-service is not a realistic solution to the patient’s need for a scan. DIF: Cognitive Level: Application 2. What are the connections between evidence-based practice and nursing research? (Select all

that apply.) a. Evidence-based care cannot be provided to patients without the nurse understanding something of research. b. A synthesis of current evidence within an area of nursing is used to improve care in that area. c. All patients with a given diagnosis should be cared for based solely on research knowledge. d. The best research evidence, clinical expertise, and patient preferences merge to produced evidence-based practice. e. Nursing research provides evidence that allows us each to practice with the same style and capability. ANS: A, B, D

Evidence-based practice in nursing requires a strong body of research knowledge that nurses must synthesize and use to promote quality care for their patients, families, and communities. In order to synthesize and use research appropriately, a nurse must understand it. A nurse must explore the best research evidence about a practice problem before using his or her clinical expertise to diagnose and manage an individual patient’s health problem. Not all patients are treated in the same way; however, nurses believe that reality varies with perception and that individual truth is relative, so they would not try to impose their views of truth and reality on patients. Rather, they would accept their patients’ views of the world and help them seek health from within those worldviews, which is a critical component of evidence-based practice. DIF: Cognitive Level: Analysis 3. What might a nursing research study address? (Select all that apply.) a. Whether having a nurse practitioner manage care is effective in decreasing

length-of-stay b. Whether nursing students learn better in an online course format, or by actual

lecture attendance c. Comparison of four types of leadership used by nurse managers, and comparison of their employees’ job satisfaction, absenteeism rates, and error rates d. Three different commonly performed surgical procedures and the mortality rate of each e. Learning specific things about the liver failure patient that can be applied to nursing practice ANS: A, B, C, E

Nursing research is defined as a scientific process that validates and refines existing knowledge and generates new knowledge that directly and indirectly influences the delivery of evidence-based nursing. Many nurses hold the view that nursing research should focus on acquiring knowledge that can be directly implemented in clinical practice, which is sometimes referred to as applied research or practical research. Some nurses may not see the value of basic research that is not immediately applicable to practice. However, research to determine effective teaching-learning strategies, the resources needed for effective nursing teams, and the strategies to prevent burnout are critical to having an adequate number of well-prepared nurses to provide high-quality care. DIF: Cognitive Level: Application 4. Which of these are suitable foci for a nursing research study? (Select all that apply.) a. The ways in which clinical nurse specialists contribute to patient outcomes b. Which elements of a nursing school curriculum remain useful for current practice,

after students graduate c. Whether requiring nurse managers to supervise more than four units is cost

effective d. What styles of physician teaching produce better diabetic compliance e. Whether patients with exacerbation of CHF are best managed with inpatient or outpatient treatment f. What the personality characteristics are of nurses in various inpatient areas ANS: A, B, C, F

Nursing research is defined as a scientific process that validates and refines existing knowledge and generates new knowledge that directly and indirectly influences the delivery of evidence-based nursing. Many nurses hold the view that nursing research should focus on acquiring knowledge that can be directly implemented in clinical practice, which is sometimes referred to as applied research or practical research. Some nurses may not see the value of basic research that is not immediately applicable to practice. However, research to determine effective teaching-learning strategies, the resources needed for effective nursing teams, and the strategies to prevent burnout are critical to having an adequate number of well-prepared nurses to provide high-quality care. DIF: Cognitive Level: Application 5. Which of the following sources generate new knowledge for nurses? (Select all that apply.) a. Editorials in nursing journals b. Qualitative research c. Adherence to hospital policies d. Research that tests a new sling scale for safety of patients and nurses e. Quantitative research

Comparison of two different insulin-dosing protocols

ANS: B, D, E

Nursing research is defined as a scientific process that validates and refines existing knowledge and generates new knowledge that directly and indirectly influences the delivery of evidence-based nursing. Nurses use a variety of research methods to test their reality and generate nursing knowledge including: quantitative research, qualitative research, outcomes research, and mixed methods research. DIF: Cognitive Level: Application 6. How are dialectic reasoning and holistic practice similar? (Select all that apply.) a. They are both based on intuition, not facts. b. They both consider the whole, rather than one part of the picture. c. Dialectic reasoning emphasizes truth, and holistic practice accepts untruth. d. They both ignore the main idea or diagnosis and concentrate on different entities. e. They both honor context and the interactions among ideas and people. f. They both break down concepts into understandable parts. g. Dialectic reasoning can be used to validate a study design whereas holistic practice

does not contribute to research. ANS: B, E, F

Dialectic reasoning involves looking at situations in a holistic way. A dialectic thinker believes that the whole is greater than the sum of the parts and that the whole organizes the parts. DIF: Cognitive Level: Synthesis 7. In nursing mentorship, as opposed to authority, the novice nurse fills which of the following

roles? (Select all that apply.) a. Counselor b. Student c. Sponsor d. Disciplinarian e. Teacher f. Questioner g. Apprentice ANS: B, F, G

An accentuated form of role-modeling is mentorship. In a mentorship, the expert nurse—or mentor—serves as a teacher, sponsor, facilitator, clinical guide, and preceptor for the novice nurse (or mentee). The mentee imitates and internalizes the values, attitudes, and behaviors of the mentor while gaining intuitive knowledge and personal experience. DIF: Cognitive Level: Analysis 8. What is the hospitalized patient’s place in evidence-based practice? (Select all that apply.) a. The patient is the recipient of the total of formal research evidence and the nurse’s

clinical expertise, and these represent his or her care plan. b. The patient brings values to the clinical encounter, which the nurse considers in

providing evidence-based care.

c. The patient’s views of truth and reality must mirror the nurse’s own worldviews

for evidence-based practice to occur. d. The patient is the focus of research, serving both as a recipient of evidence-based

research and the subject of future evidence, based on data collected now from the patient. e. The patient’s needs and values merge with best research and clinical expertise to produce evidence-based practice. ANS: B, E

Nurses understand that reality varies with perception and that individual truth is relative. Consequently, they would not try to impose their views of truth and reality on patients. Rather, they would accept patients’ views of the world and help them seek health from within those worldviews, which is a critical component of evidence-based practice. The best research evidence, clinical expertise, and patient needs and values merge to produce evidence-based practice. DIF: Cognitive Level: Analysis

Chapter 02: Evolution of Research in Building Evidence-Based Nursing Practice Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. In which way did Florence Nightingale contribute most substantially to evidence-based

practice? a. She conducted outcomes research about the power of nursing for creating change. b. She was the first woman elected to the Royal Statistical Society. c. She collected and analyzed data that changed the care of hospitalized soldiers. d. She calculated mortality rates under varying conditions. ANS: C

Nightingale collected data on soldier morbidity and mortality rates and the factors influencing them and presented her results in tables and pie charts, a sophisticated type of data presentation for the period. Nightingale’s research enabled her to instigate attitudinal, organizational, and social changes. She changed the attitudes of the military and society toward the care of the sick. The military began to view the sick as having the right to adequate food, suitable quarters, and appropriate medical treatment, which greatly reduced the mortality rate. DIF: Cognitive Level: Application 2. If a nurse manager wants to study how well last year’s policies governing implementation of a

“bundle” of interventions to prevent cross-contamination of MRSA has been working in the manager’s units, which of the following strategies would the manager be most likely to use? a. Outcomes research b. Mixed methods research c. Ethnographic research d. Experimental research ANS: A

Outcomes research emerged as an important methodology for documenting the effectiveness of healthcare services in the 1980s and 1990s. This type of research evolved from the quality assessment and quality assurance functions that originated with the professional standards review organizations (PSROs) in 1972. During the 1980s, William Roper, the director of the Health Care Finance Administration (HCFA), promoted outcomes research for determining the quality and cost-effectiveness of patient care. Mixed methods research is conducted when the study problem and purpose are best addressed using both quantitative and qualitative research methodologies. Ethnography attempts to tell the story of people’s daily lives while describing the culture in which they live. Experimental research is an objective, systematic, controlled investigation conducted for the purpose of predicting and controlling phenomena. This type of research examines causality through rigorous control of variables. DIF: Cognitive Level: Analysis 3. A researcher publishes a paper describing and explaining how faith, pain, adherence to

therapy, and meditation interact during the rehabilitation process. The description of the process is based on many interviews the researcher conducted with persons during and following rehabilitation experiences. Which type of methodology did this research employ?

a. b. c. d.

Ethnography Phenomenology Exploratory-descriptive Grounded theory

ANS: D

Grounded theory methodology emphasizes interaction, observation, and descriptions of relationships among concepts. Throughout the study, the researcher explores, proposes, formulates, and validates relationships among the concepts until a theory evolves. The theory developed is grounded in, or has its roots in, the data from which it was derived. Ethnography attempts to tell the story of people’s daily lives while describing the culture in which they live. Phenomenology explores an experience as it is lived by the study participants and reported from participants’ points of view. Exploratory-descriptive qualitative research is conducted to address an issue or problem in need of a solution or understanding. DIF: Cognitive Level: Analysis 4. A panel of researchers conducts several studies, all drawn from an existent hospital and clinic

database. The studies focus on quality and effectiveness within that system. The specific studies address mortality rates in elders within a year after hip fracture, functional outcomes 6 months after admission to a neurosurgical ICU after traumatic brain injury, rate of nurse injuries in an emergency department, and number of patient falls on various floors of the hospital. What type of research is this? a. Experimental research b. Outcomes research c. Ethnographic research d. Grounded theory research ANS: B

Outcomes research emerged as an important methodology for documenting the effectiveness of healthcare services in the 1980s and 1990s. This type of research evolved from the quality assessment and quality assurance functions that originated with the professional standards review organizations (PSROs) in 1972. During the 1980s, William Roper, the director of the Health Care Finance Administration (HCFA), promoted outcomes research for determining the quality and cost-effectiveness of patient care. Experimental research is an objective, systematic, controlled investigation conducted for the purpose of predicting and controlling phenomena. This type of research examines causality through rigorous control of variables. Ethnography attempts to tell the story of people’s daily lives while describing the culture in which they live. Grounded theory methodology emphasizes interaction, observation, and descriptions of relationships among concepts. DIF: Cognitive Level: Application 5. A researcher designs a study. The data are collected by means of a questionnaire, the study

has a clear purpose statement, the results are presented as a narrative without statistical analysis, and the suggestions made for practice are worded as general suggestions. What type of research is this? a. Qualitative research b. Quantitative research c. Mixed methods research d. Meta-analysis

ANS: A

Quantitative research is a formal, objective, systematic process implemented to obtain numerical data, which are then analyzed statistically for generating understanding of various aspects of the world. Qualitative research is also systematic, but it is an interactive, naturalistic, and subjective approach that results in a narrative. Mixed methods research most commonly uses both quantitative and qualitative approaches, producing both statistical analysis and narrative. Meta-analysis is the statistical pooling of results from previous studies into a single quantitative analysis that provides one of the highest levels of evidence about an intervention’s effectiveness. DIF: Cognitive Level: Application 6. A newly employed nurse administrator wants to know more about the employees on the units

the administrator supervises. The manager accesses the managerial database and gathers data about all of the current employees on the unit, including work shift, number of years employed, age, gender, educational preparation, certifications, work history, and professional accomplishments, analyzing the data statistically. What type of quantitative research is this? a. Descriptive research b. Correlational research c. Quasi-experimental research d. Experimental research ANS: A

The quantitative research methods are classified into four categories: (1) descriptive, which defines the magnitude of a concept and its characteristics, (2) correlational, which determines association between or among variables, (3) quasi-experimental, which tests an intervention and lacks control in at least one of three areas, and (4) experimental, which tests an intervention and includes both a control group and random assignment. This is a research study, even though it depends upon existent data, collected by another manager. Its purpose is to describe the employees. DIF: Cognitive Level: Analysis 7. A human resources employee performs research focusing on the professional life span of

nurses within this particular institution and tries to discover whether their choice of work area is connected with the number of years they work in the institution. What type of quantitative research is this? a. Descriptive research b. Correlational research c. Quasi-experimental research d. Experimental research ANS: B

The quantitative research methods are classified into four categories: (1) descriptive, which defines the magnitude of a concept and its characteristics, (2) correlational, which determines association between or among variables, (3) quasi-experimental, which tests an intervention and lacks control in at least one of three areas, and (4) experimental, which tests an intervention and includes both a control group and random assignment. This study investigates the connection or association between work area and length of time worked.

DIF: Cognitive Level: Analysis 8. In an attempt to assess whether selection of a same-gender psychiatrist leads to better mental

health outcomes, clients newly referred for mental health services are told they may choose their own psychiatrists. At the beginning of treatment, and again after 3 months of therapy, measures of mental health are performed. What type of quantitative research is this? a. Descriptive research b. Correlational research c. Quasi-experimental research d. Experimental research ANS: C

The quantitative research methods are classified into four categories: (1) descriptive, which defines the magnitude of a concept and its characteristics, (2) correlational, which determines association between or among variables, (3) quasi-experimental, which tests an intervention and lacks control in at least one of three areas, and (4) experimental, which tests an intervention and includes both a control group and random assignment. This research study is designed to test an intervention but does not include random assignment, one of the requisites of experimental research. DIF: Cognitive Level: Analysis 9. In a rehabilitation unit, patients are randomly assigned to high fiber diets versus ordinary fiber

diets, in order to measure the effect on constipation. What type of quantitative research is this? a. Descriptive research b. Correlational research c. Quasi-experimental research d. Experimental research ANS: D

The quantitative research methods are classified into four categories: (1) descriptive, which defines the magnitude of a concept and its characteristics, (2) correlational, which determines association between or among variables, (3) quasi-experimental, which tests an intervention and lacks either a control group or random assignment, and (4) experimental, which tests an intervention and includes both a control group and random assignment. This research study tests an intervention and includes both a control group and random assignment. DIF: Cognitive Level: Analysis 10. A researcher uses interviews with two or three open-ended questions to study women in the

staging phase of breast cancer treatment, in order to understand their experiences and the meanings they attribute to those experiences. What type of research is this? a. Phenomenological research b. Grounded theory research c. Ethnographic research d. Exploratory-descriptive qualitative research ANS: A

Phenomenology explores an experience as it is lived by the study participants and reported from participants’ points of view. Grounded theory methodology emphasizes interaction, observation, and descriptions of relationships among concepts. Ethnography attempts to tell the story of people’s daily lives while describing the culture in which they live. Exploratory-descriptive qualitative research is conducted to address an issue or problem in need of a solution or understanding. DIF: Cognitive Level: Analysis 11. A researcher uses an interview with eight open-ended questions to study women in a new

multi-staging phase of breast cancer treatment, which includes serial biopsies and necessitates weekly closed biopsy, in order to understand more about social factors that impinge upon their experience. What type of research is this? a. Phenomenological research b. Grounded theory research c. Ethnographic research d. Exploratory-descriptive qualitative research ANS: B

Grounded theory methodology emphasizes interaction, observation, and descriptions of relationships among concepts. Throughout the study, the researcher explores, proposes, formulates, and validates relationships among the concepts until a theory evolves. The theory developed is grounded in, or has its roots in, the data from which it was derived. Ethnography attempts to tell the story of people’s daily lives while describing the culture in which they live. Exploratory-descriptive qualitative research is conducted to address an issue or problem in need of a solution or understanding. Phenomenology explores an experience as it is lived by the study participants and reported from participants’ points of view. DIF: Cognitive Level: Analysis 12. A researcher conducts many interviews, over a 1-year period, with women in the treatment

phase of breast cancer, all of whom are attending a breast cancer support group, in order to understand what happens in the support group, how the members are affected by membership, and how the members contribute to the group. The researcher herself is also in treatment for breast cancer and is a member of the support group. What type of research is this? a. Phenomenological research b. Grounded theory research c. Ethnographic research d. Exploratory-descriptive qualitative research ANS: C

Ethnography attempts to tell the story of people’s daily lives while describing the culture in which they live. The researcher may live in or become part of the cultural setting to gather the data. Phenomenology explores an experience as it is lived by the study participants and reported from participants’ points of view. Grounded theory methodology emphasizes interaction, observation, and descriptions of relationships among concepts. Exploratory-descriptive qualitative research is conducted to address an issue or problem in need of a solution or understanding. DIF: Cognitive Level: Analysis

13. A researcher investigates the cause-and-effect relationship between the incidence of children’s

spinal cord injury and the current state law requiring that all children under the age of 8 will ride in special car harnesses. Which form of nursing research should the researcher employ? a. Meta-analysis b. Mixed methods research c. Qualitative research d. Quantitative research ANS: D

Quantitative research is a formal, objective, systematic process implemented to obtain numerical data, which are then analyzed statistically for generating understanding of various aspects of the world. Qualitative research is also systematic, but it is an interactive, naturalistic, and subjective approach that results in a narrative. Mixed methods research most commonly uses both quantitative and qualitative approaches, producing both statistical analysis and narrative. Meta-analysis is the statistical pooling of results from previous studies into a single quantitative analysis that provides one of the highest levels of evidence about an intervention’s effectiveness. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. Florence Nightingale researched mortality and morbidity rates in soldiers during the Crimean

War and investigated various factors that influenced both, presenting her results as pie charts and graphs. Consequently, it is known that she conducted which types of research? (Select all that apply.) a. Phenomenological research b. Causational research c. Descriptive research d. Correlational research e. Ethnographic research ANS: C, D

Nightingale is noted for her data collection and statistical analyses during the Crimean War. She gathered data on soldier morbidity and mortality rates and the factors influencing them and presented her results in tables and pie charts, a sophisticated type of data presentation for the period. There is no evidence that she designed causational (experimental or quasi-experimental) research or any type of qualitative research. DIF: Cognitive Level: Analysis 2. Which statements about quantitative research are accurate? (Select all that apply.) a. The results of quantitative research should be generalized back to the population

from which the sample was drawn. b. The methods of quantitative research are consistent with the philosophy of logical c. d. e. f.

positivism. Quantitative research addresses quantities, relationships, and causes. Quantitative research predominates in the nursing research literature. Quantitative research is always experimental. Quantitative research tells the story of the research participants’ daily lives, within

their culture. ANS: A, B, C, D

The quantitative methodology is used to describe variables, examine relationships among variables, and determine cause-and-effect interactions between variables. In this text, the quantitative research methods are classified into four categories: (1) descriptive, (2) correlational, (3) quasi-experimental, and (4) experimental. Quantitative research utilizes statistical analyses to reduce and organize data, describe variables, examine relationships, and determine differences among groups. The quantitative approach to scientific inquiry emerged from a branch of philosophy called logical positivism, which operates on strict rules of logic, truth, laws, axioms, and predictions. Generalization involves the application of trends or general tendencies (which are identified by studying a sample) to the population from which the research sample was drawn. Researchers must be cautious in making generalizations, because a sound generalization requires the support of many studies with a variety of samples. Ethnography attempts to tell the story of people’s daily lives while describing the culture in which they live. DIF: Cognitive Level: Analysis 3. Which statements about qualitative research are accurate? (Select all that apply.) a. Qualitative research findings may be generalized. b. Qualitative research generates information that can contribute to theory formation. c. Qualitative research yields data such as audiotapes, videotapes, field notes, and d. e. f. g.

other data that are based on language, not numbers. Qualitative research is not systematic. Qualitative research does not contain or imply a purpose. Qualitative researchers interpret the meaning revealed to them by the participants. Qualitative research is uncontrolled.

ANS: B, C, F

The findings from a qualitative study are unique to that study, and it is not the researcher’s intent to generalize the findings to a larger population. Throughout the study, the grounded theory researcher explores, proposes, formulates, and validates relationships among the concepts until a theory evolves. Qualitative researchers use observations, interviews, and focus groups to gather data. Qualitative data take the form of words that are recorded on paper or electronically. Qualitative research is a systematic, interactive, subjective, naturalistic, scholarly approach used to describe life experiences, cultures, and social processes from the perspectives of the persons involved. The problem and purpose to be studied determine the type of research to be conducted, and the researcher’s knowledge of both types of research promotes accurate selection of the methodology for the problem identified. Qualitative researchers are encouraged to question generalizations and to interpret meaning based on individual study participants’ perceptions and realities. DIF: Cognitive Level: Analysis 4. Which of the following are true of quantitative research and quantitative researchers? (Select

all that apply.) a. Quantitative research addresses human responses by measuring or counting them. b. Quantitative research presents information by clustering it or counting it. c. Quantitative researchers maintain objectivity in their data collection and data analysis methods.

d. Quantitative research describes variables, relationships among variables, and

differences among groups. e. Precision is not especially important in quantitative research. f. Quantitative researchers operate in a concrete realm. g. All quantitative research findings can be generalized. ANS: A, B, C, D, F

The quantitative approach to scientific inquiry emerged from a branch of philosophy called logical positivism, which operates on strict rules of logic, truth, laws, axioms, and predictions. Quantitative researchers hold the position that truth is absolute and that there is a single reality that one could define by careful measurement. The quantitative researcher must be completely objective, never allowing values, feelings, or personal perceptions to enter into the measurement of reality. Quantitative researchers believe that all human behavior is objective, purposeful, and measurable. Quantitative research requires the use of (1) structured interviews, questionnaires, or observations, (2) scales, or (3) physiological measures that generate numerical data. Statistical analyses are conducted to reduce and organize data, describe variables, examine relationships, and determine differences among groups. Control, precise measurement methods, and statistical analyses are used to ensure that the research findings accurately reflect reality so that the study findings can be generalized. Generalization involves the application of trends or general tendencies (which are identified by studying a sample) to the population from which the research sample was drawn. Researchers must be cautious in making generalizations, because a sound generalization requires the support of many studies with a variety of samples. DIF: Cognitive Level: Analysis 5. Ethnographic research might focus upon which topics? (Select all that apply.) a. Bacterial cultures b. Cultural beliefs of the ancient Romans c. How children in Alaska play during the winter d. The members of Alcoholics Anonymous who share 20 years of abstinence e. The mentoring process in a labor-delivery unit f. Conversational Spanish ANS: C, D, E

Ethnographic research was developed by anthropologists to investigate cultures through an in-depth study of the members of the culture. Ethnographic research attempts to tells the story of people’s daily lives while describing the culture in which they live. The ethnographic research process is the systematic collection, description, and analysis of data to develop a description of cultural behavior. The researcher (ethnographer) may be present in the cultural setting itself, both before and during data collection. Sometimes the researcher is a part of the culture or becomes a part of it, to facilitate data collection. Ethnographic researchers describe, compare, and contrast different cultures to add to our understanding of the impact of culture on human behavior and health. DIF: Cognitive Level: Analysis 6. A researcher is operating from the point of view of logical positivism. Which research

methods would the logical positivist use? (Select all that apply.) a. Grounded theory research b. Correlational research

c. d. e. f.

Historical research Quasi-experimental research Quantitative descriptive research Exploratory-descriptive qualitative research

ANS: B, D, E

principal topics for the next wave of nursing research, in the first half of the 20th century? (Select all that apply.) a. Evidence-based practice (EBP) b. Primary nursing’s advantages in hospitals c. Nursing education, as opposed to nurse training d. The nursing process and nursing diagnosis e. Staffing, patient assignments, and type of care ANS: C, E

From 1900 to 1950, research activities in nursing were limited, but a few national studies were conducted related to nursing education. These studies included the Nutting Report, 1912; Goldmark Report, 1923; and Burgess Report, 1926. On the basis of recommendations of the Goldmark Report, more schools of nursing were established in university settings. The baccalaureate degree in nursing provided a basis for graduate nursing education, with the first master of nursing degree offered by Yale University in 1929. A research trend that started in the 1940s and continued in the 1950s focused on the organization and delivery of nursing services. Studies were conducted on the numbers and kinds of nursing personnel, staffing patterns, patient classification systems, patient and nurse satisfaction, and unit arrangement. Types of care such as comprehensive care, home care, and progressive patient care were evaluated. In the 1970s, the nursing process became the focus of many studies, with the investigations of assessment techniques, nursing diagnoses classification, goal-setting methods, and specific nursing interventions. Primary nursing care, which involves the delivery of patient care predominantly by registered nurses (RNs), was the trend for the 1970s. The vision for nursing research in the 21st century includes conducting quality studies through the use of a variety of methodologies, synthesizing the study findings into the best research evidence, using this research evidence to guide practice, and examining the outcomes of EBP. DIF: Cognitive Level: Synthesis 8. Which statements are true of the Cochrane Center and Cochrane Collaboration, begun in the

1970s by Professor Archie Cochrane? (Select all that apply.) a. It was originally called the Walter Reed Army Institute of Research. b. It developed the original master’s degrees in nursing practice. c. It serves as a repository for evidence-based practice guidelines.

d. It was the first association to publish a nursing research journal. e. It is the online library resource for research literature reviews. ANS: C, E

Professor Archie Cochrane originated the concepts of evidence-based practice in his book Effectiveness and Efficiency: Random Reflections on Health Services. Cochrane advocated the provision of health care based on research to improve the quality of care and patient outcomes. To facilitate the use of research evidence in practice, the Cochrane Center was established in 1992, and the Cochrane Collaboration in 1993. The Cochrane Collaboration and Library house numerous evidence-based practice resources, such as systematic reviews of research and evidence-based guidelines for practice. A Department of Nursing Research was established in the Walter Reed Army Institute of Research in 1957. This was the first nursing unit in a research institution that emphasized clinical nursing research. The baccalaureate degree in nursing provided a basis for graduate nursing education, with the first master of nursing degree offered by Yale University in 1929. The Association of Collegiate Schools of Nursing, organized in 1932 and later renamed the American Association of Colleges of Nursing (AACN), promoted the conduct of research to improve education and practice, also sponsoring the publication of the first research journal in nursing, Nursing Research, in 1952 (Fitzpatrick, 1978). DIF: Cognitive Level: Evaluation 9. How does quantitative research contribute to evidence-based practice? (Select all that apply.) a. It provides facts that nurses can add to their knowledge base. This makes practice

more objective and quantifiable. b. It provides scientific support for policies already in place. More evidence makes an

existent policy more defensible. c. It provides evidence of opposing policies already in place. Evidence in opposition to policies may result in new policies. d. It allows the nurse to understand the personal experience of illness and the meaning the client attaches to it. This engenders compassion. e. It contributes evidence that will make nursing practice almost completely evidence-based, eliminating different styles of nursing practice. ANS: B, C

Quantitative research is best defined as a formal, objective, systematic study process implemented to obtain numerical data in order to answer a research question. This research method is used to describe variables, examine relationships among variables, and determine cause-and-effect interactions between variables. Evidence-based practice is the conscientious integration of best research evidence with clinical expertise and patient values and needs in the delivery of quality, cost-effective health care. Best research evidence is a summary of the highest quality, current empirical knowledge in a specific area of health care that is developed from a synthesis of quality studies in that area. Consequently, new research can affect the sum total of research evidence. The qualitative research method of phenomenology allows understanding of the lived experience and the meaning it engenders. The aim of phenomenology is to explore an experience as it is lived by the study participants and interpreted by the researcher. DIF: Cognitive Level: Analysis 10. What does appropriate generalization require? (Select all that apply.)

a. b. c. d. e.

Any type of sample, whether or not it is representative Application of findings to the population from which the sample was drawn More than one research study using the same research questions and variables Statistical analysis that shows consistent results across studies One single study with strong results

ANS: B, C, D

Statistical analyses are conducted to reduce and organize data, describe variables, examine relationships, and determine differences among groups. Control, precise measurement methods, and statistical analyses are used to ensure that the research findings accurately reflect reality so that the study findings can be generalized. Generalization involves the application of trends or general tendencies (which are identified by studying a sample) to the population from which the research sample was drawn. The sample must represent the population. Researchers must be cautious in making generalizations, because a sound generalization requires the support of many studies with a variety of samples. Replicating or repeating of studies with similar methodology adds to the quality of the research evidence. DIF: Cognitive Level: Analysis 11. What best characterizes the contribution of qualitative nursing research to evidence-based

practice? (Select all that apply.) a. It presents collective common evidence of healthcare clients’ experiences, which may provide inspirations for individual practice. b. It provides stories of how healthcare clients feel. This lets nurses know what people in similar circumstances can be expected to experience and feel. c. It provides evidence that determines how nurses should interact with various cultures. This mandates action. d. Its purpose is to test theory. e. It reveals participants’ experiences and individual viewpoints, feelings, and interpretations. These can provide guidelines for client-centered care. ANS: A, E

Qualitative research is a systematic, interactive, subjective, naturalistic, scholarly approach used to describe life experiences, cultures, and social processes from the perspectives of the persons involved. This type of research is conducted to explore, describe, and promote understanding of human experiences, events, and cultures over time. The findings from a qualitative study are unique to that study, and it is not the researcher’s intent to generalize the findings to a larger population: what the participants experience, perceive, or feel is not generalizable to others. Because of this, the results may be used only to inform individual practice, perhaps contributing to nurse expertise, or to provide general guidelines without a mandate for practice. DIF: Cognitive Level: Analysis 12. In which ways does the Quality and Safety Education for Nurses (QSEN) initiative relate to

research? (Select all that apply.) a. One of its six competencies for nursing education is evidence-based practice. This implies that evidence will be generated through systematic research. b. QSEN funds current research projects, both quantitative and qualitative. c. The QSEN initiative specifies the number of research projects that teaching hospitals must conduct yearly, in order to meet expectations.

d. One of the expectations of nurses after graduate education is to be able to develop

policies for practice that are based on research. e. It specifies that nurses will be able to integrate best current evidence with clinical

expertise and patient preferences. This presupposes that there is current research evidence. ANS: A, D, E

The Quality and Safety Education for Nurses initiative identified the following six essential competencies for nursing education: patient-centered care, teamwork and collaboration, EBP, quality improvement, safety, and informatics. The QSEN Program is focused on developing the requisite knowledge, skills, and attitude (KSA) statements for each of the competencies for pre-licensure and graduate education. Since 2007, the QSEN Institute website has provided teaching strategies and resources to facilitate the accomplishments of the QSEN competencies in nursing education programs. The EBP competency is defined as “integrating the best current evidence with clinical expertise and patient/family preferences and values for delivery of optimal health care.” Graduate level nursing students need to have KSAs to conduct critical appraisals of studies; summarize current research evidence; develop protocols, algorithms, and policies for use in practice based on research; and participate in the conduct of research activities. Part of developing an EBP is maintaining knowledge of current research. QSEN does not fund independent research, nor does it mandate yearly research requirements for hospitals or other institutions. DIF: Cognitive Level: Analysis 13. How does the QSEN initiative apply to nursing graduate students? (Select all that apply.) a. QSEN guidelines for nurses with master’s degrees include designing multiple b. c. d. e.

research projects and independently conducting such research. Participation in ongoing research may be a job expectation in an advanced practice role. Revisions to the QSEN knowledge, skills, and attitude (KSA) statements are generated from research. Summarizing current research is required both within a nursing master’s program and subsequent to attaining the master’s degree. Nurses with advanced degrees may be called upon to participate in healthcare team activities that generate decision trees for bedside nurses to use in patient care.

ANS: A, D, E

The Quality and Safety Education for Nurses initiative identified the following six essential competencies for nursing education: patient-centered care, teamwork and collaboration, EBP, quality improvement, safety, and informatics. The QSEN Program is focused on developing the requisite knowledge, skills, and attitude (KSA) statements for each of the competencies for pre-licensure and graduate education. Since 2007, the QSEN Institute website has provided teaching strategies and resources to facilitate the accomplishments of the QSEN competencies in nursing education programs. The EBP competency is defined as “integrating the best current evidence with clinical expertise and patient/family preferences and values for delivery of optimal health care.” Graduate level nursing students need to have KSAs to conduct critical appraisals of studies; summarize current research evidence; develop protocols, algorithms, and policies for use in practice based on research; and participate in the conduct of research activities. An expanded knowledge of research is an important part of developing an EBP and is necessary to accomplish the QSEN competencies.

DIF: Cognitive Level: Analysis

Chapter 03: Introduction to Quantitative Research Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A researcher conducts a study to determine the effectiveness of a special program of

sensitivity training for nurse managers upon several outcomes, all related to their staff’s ability to identify and intervene appropriately when medication errors occur. This is an example of what type of quantitative research? a. Applied research b. Basic research c. Descriptive research d. Qualitative research ANS: A

Applied research focuses on generating knowledge that will directly influence or improve practice. This type of research is conducted to solve real-life problems, to make decisions, or to predict or control outcomes in real-life practice situations. Basic research is conducted in a research laboratory or other artificial setting with animals, paid human volunteers, or animal or human tissue. Descriptive research is the exploration and description of phenomena in real-life situations. Qualitative research is conducted to explore, describe, and promote understanding of human experiences, situations, events, and cultures over time. DIF: Cognitive Level: Application 2. A researcher randomly assigns a large group of subjects who are hospital patients either to

receive magnesium at bedtime or not to receive magnesium at bedtime, and then measures sleep quality and duration. What type or research is this? a. Correlational research b. Experimental research c. Descriptive research d. Quasi-experimental research ANS: B

All non-interventional research is essentially descriptive, in that it describes either variables or relationships between variables: the researcher examines subjects as they are without manipulation. Non-interventional research includes both correlational and descriptive designs. In experimental research, the researcher applies an intervention to the experimental subjects but not to the control subjects, and then measures the effect on a dependent variable. In addition, in experimental research, subjects must be randomly assigned to either the intervention group or the control group. Quasi-experimental research is similar to experimental research, but lacks (1) the presence of at least one separate and distinct control group and (2) random assignment to group. DIF: Cognitive Level: Analysis

3. A research study contains the following in its Introduction section: “This study was

undertaken to explore the effect of massage on total hours of sleep per 24-hour day, in persons averaging fewer than 7 hours of sleep per night, attributable to insomnia. Presumably by increasing endorphin levels, massage seems to provide an immediate relaxation and an ability to sleep immediately following the session, but it is unclear whether these benefits actually extend to total sleep, despite anecdotal support. The claim that massage increases total hours of sleep has been inadequately researched. Does massage increase the total number of hours of daily sleep? It was posited that provision of daily late-morning massage would affect total hours of sleep per 24-hour day. The study’s causational explanation was based on the physiological matrix of McCarthy, which includes effects of endorphins on sleep, learning ability, pain, digestive function, and cardiac output. It was taken as established fact that massage is pleasant, that research subjects getting fewer than 7 hours of sleep per night were sleep-deprived, and that endorphins mediated the changes observed.” Select the research problem. a. This study was undertaken to explore the effect of massage on total hours of sleep per 24-hour day, in persons averaging fewer than 7 hours of sleep per night, attributable to insomnia b. It was posited that provision of daily late-morning massage would affect total hours of sleep per 24-hour day. c. It was taken as established fact that massage is pleasant, that research subjects getting fewer than 7 hours of sleep per night were sleep-deprived, and that endorphins mediated the changes observed. d. Presumably by increasing endorphin levels, massage seems to provide an immediate relaxation and an ability to sleep immediately following the session, but it is unclear whether these benefits actually extend to total sleep, despite anecdotal support. ANS: D

There is a gap in nursing’s knowledge base. This gap may relate only to general understanding or it may have practice implications. Perhaps it represents an area in which theoretical knowledge is incomplete. A research problem statement addresses the current state of knowledge about a phenomenon for a given population, following the brief summary with a sentence that identifies the gap. DIF: Cognitive Level: Analysis 4. A research study contains the following in its Introduction section: “This study was

a. It was taken as established fact that massage is pleasant, that research subjects

getting fewer than 7 hours of sleep per night were sleep-deprived, and that endorphins mediated the changes observed. b. Presumably by increasing endorphin levels, massage seems to provide an immediate relaxation and an ability to sleep immediately following the session, but it is unclear whether these benefits actually extend to total sleep, despite anecdotal support. c. It was posited that provision of daily late-morning massage would affect total hours of sleep per 24-hour day. d. The study’s causational explanation was based on the physiological matrix of McCarthy, which includes effects of endorphins on sleep, learning ability, pain, digestive function, and cardiac output. ANS: D

A framework is a combination of concepts and the connections between them, used to explain relationships. The framework should both guide the research and help the reader of the research report to understand the connections among study variables. Most stated frameworks in research reports are midrange nursing theories or midrange theories developed in related disciplines, such as psychology, physiology, or sociology. DIF: Cognitive Level: Analysis 5. A research study contains the following in its Introduction section: “This study was

undertaken to explore the effect of massage on total hours of sleep per 24-hour day, in persons averaging fewer than 7 hours of sleep per night, attributable to insomnia. Presumably by increasing endorphin levels, massage seems to provide an immediate relaxation and an ability to sleep immediately following the session, but it is unclear whether these benefits actually extend to total sleep, despite anecdotal support. The claim that massage increases total hours of sleep has been inadequately researched. Does massage increase the total number of hours of daily sleep? It was posited that provision of daily late-morning massage would affect total hours of sleep per 24-hour day. The study’s causational explanation was based on the physiological matrix of McCarthy, which includes effects of endorphins on sleep, learning ability, pain, digestive function, and cardiac output. It was taken as established fact that massage is pleasant, that research subjects getting fewer than 7 hours of sleep per night were sleep-deprived, and that endorphins mediated the changes observed.” Select the research assumption. a. This study was undertaken to explore the effect of massage on total hours of sleep per 24-hour day, in persons averaging fewer than 7 hours of sleep per night, attributable to insomnia. b. It was posited that provision of daily late-morning massage would affect total hours of sleep per 24-hour day. c. It was taken as established fact that massage is pleasant, that research subjects getting fewer than 7 hours of sleep per night were sleep-deprived, and that endorphins mediated the changes observed. d. Presumably by increasing endorphin levels, massage seems to provide an immediate relaxation and an ability to sleep immediately following the session, but it is unclear whether these benefits actually extend to total sleep, despite anecdotal support. The claim that massage increases total hours of sleep has been inadequately researched.

ANS: C

Assumptions are beliefs that are accepted as true, without proof. It is important that researchers make explicit their assumptions related to the conduct of the research. This involves a considerable amount of reflection on the researcher’s part because if the assumptions are not true, the research findings will not be credible. DIF: Cognitive Level: Analysis 6. A research study contains the following in its Introduction section: “This study was

undertaken to explore the effect of massage on total hours of sleep per 24-hour day, in persons averaging fewer than 7 hours of sleep per night, attributable to insomnia. Presumably by increasing endorphin levels, massage seems to provide an immediate relaxation and an ability to sleep immediately following the session, but it is unclear whether these benefits actually extend to total sleep, despite anecdotal support. The claim that massage increases total hours of sleep has been inadequately researched. Does massage increase the total number of hours of daily sleep? It was posited that provision of daily late-morning massage would affect total hours of sleep per 24-hour day. The study’s causational explanation was based on the physiological matrix of McCarthy, which includes effects of endorphins on sleep, learning ability, pain, digestive function, and cardiac output. It was taken as established fact that massage is pleasant, that research subjects getting fewer than 7 hours of sleep per night were sleep-deprived, and that endorphins mediated the changes observed.” Select the research purpose. a. This study was undertaken to explore the effect of massage on total hours of sleep per 24-hour day, in persons averaging fewer than 7 hours of sleep per night, attributable to insomnia. b. It was posited that provision of daily late-morning massage would affect total hours of sleep per 24-hour day. c. Presumably by increasing endorphin levels, massage seems to provide an immediate relaxation and an ability to sleep immediately following the session, but it is unclear whether these benefits actually extend to total sleep, despite anecdotal support. The claim that massage increases total hours of sleep has been inadequately researched. d. The study’s causational explanation was based on the physiological matrix of McCarthy, which includes effects of endorphins on sleep, learning ability, pain, digestive function, and cardiac output. ANS: A

The research purpose is a short, usually one-sentence, statement. In a research proposal, it begins in the present tense, and in a research report, in the past tense. The purpose statement makes mention of the major study variables, the population, and sometimes the setting, and it hints at the general type of study. DIF: Cognitive Level: Analysis

7. A research study contains the following in its Introduction section: “This study was

undertaken to explore the effect of massage on total hours of sleep per 24-hour day, in persons averaging fewer than 7 hours of sleep per night, attributable to insomnia. Presumably by increasing endorphin levels, massage seems to provide an immediate relaxation and an ability to sleep immediately following the session, but it is unclear whether these benefits actually extend to total sleep, despite anecdotal support. The claim that massage increases total hours of sleep has been inadequately researched. Does massage increase the total number of hours of daily sleep? It was posited that provision of daily late-morning massage would affect total hours of sleep per 24-hour day. The study’s causational explanation was based on the physiological matrix of McCarthy, which includes effects of endorphins on sleep, learning ability, pain, digestive function, and cardiac output. It was taken as established fact that massage is pleasant, that research subjects getting fewer than 7 hours of sleep per night were sleep-deprived, and that endorphins mediated the changes observed.” Select the research question. a. This study was undertaken to explore the effect of massage on total hours of sleep per 24-hour day, in persons averaging fewer than 7 hours of sleep per night, attributable to insomnia. b. It was posited that provision of daily late-morning massage would affect total hours of sleep per 24-hour day. c. Does massage increase the total number of hours of daily sleep? d. Presumably by increasing endorphin levels, massage seems to provide an immediate relaxation and an ability to sleep immediately following the session, but it is unclear whether these benefits actually extend to total sleep, despite anecdotal support. ANS: C

Research questions are actual questions that address the relationship between variables. DIF: Cognitive Level: Analysis 8. A researcher conducting a study to examine linkages among age, gender, driver’s license

suspension, zip code, poverty, educational level, and income, sourced from the records of the State Department of Motor Vehicles, is using which type of research? a. Descriptive research b. Correlational research c. Problem solving d. Experimental ANS: B

Descriptive research is the exploration and description of phenomena in real-life situations. Correlational research involves the systemic investigation of relationships between or among variables. In descriptive and correlational studies, no treatment is administered, so the study design is nonexperimental and centers on describing variables, examining relationships, and improving the precision of measurement. Problem solving is a strategy, not a type of research. Experimental research is one of the two principal design groups in interventional research. Its purpose is to test the null hypothesis by means of applying an intervention to experimental subjects but not to the control subjects, and then measuring the effect on a dependent variable DIF: Cognitive Level: Application

9. A student completes a master’s thesis on correlates of depression in retired airline pilots, and

the thesis is shelved in the library. Has this student communicated these research findings, and why or why not? a. Yes, because the thesis is in the library and can be accessed. b. No, because the findings have not been made available to persons who will utilize them. c. Yes, because the students in this particular master’s program often discuss their work in progress. d. No, because if the findings do not appear in print in a nursing journal, they have not been communicated. ANS: B

Research is not considered complete until the findings have been communicated. Communicating research findings involves developing and disseminating a research report to appropriate audiences; the research report is disseminated through presentations and publications. Analyzing data, drawing conclusions, and writing a report of the findings are essential steps in conducting research—but they do not complete the process. DIF: Cognitive Level: Analysis 10. A researcher studies the effect upon dental caries formation of a year-long regimen of daily

rinsing with a particularly noxious-flavored oral solution, only to discover that 285 of the 300 subjects in the study have withdrawn from it by the end of the first month. Which step in the research process was not properly undertaken? a. Defining the purpose b. Conducting the literature review c. Selecting study variables d. Performing a pilot study ANS: D

A pilot study is a small-scale investigation conducted preparatory to a subsequent adequately powered trial. The purpose of the usual pilot study is to determine whether the proposed methods are effective in locating and consenting subjects, and in collecting useful data. Most pilot studies are feasibility studies. Pilot research can determine whether subjects will actually consent to study participation, how many subjects are really available, how much time is required to gather data on one subject, how well instruments work, whether an intervention produces a measurable difference in the dependent variable, and how large that difference is. In addition, for quantitative studies a statistical analysis of pilot results often is performed, so that the power analysis estimation of the number of subjects needed for statistical significance can be recalculated, assuring an adequate sample. DIF: Cognitive Level: Application 11. A researcher studies the effect of three, 1-hour counseling sessions on eliminating bullying

behaviors in teenagers. For the dependent variable, the researcher selects the outcome of being reported to the principal’s office in the 2 weeks following the sessions. The sample consists of the 18 high schools in a large metropolitan area. The results of the research are dismissed by reviewers as meaningless, severely limiting generalization. What is the problem here? a. Construct validity limitations b. Not enough independent variables c. External validity limitations

d. Inadequate sample size ANS: A

Limitations are aspects of the study that diminish the credibility of study findings and conclusions or restrict the population to which findings can be generalized. These may or may not be results of problems or weaknesses of the study. There are four types of limitations. Construct limitations, sometimes called theoretical limitations, are failures of logic, which limit the ability to interpret study findings on the theoretical level, at the application level, or both. In this study, the principal construct validity problems are (1) the short, 2-week measuring period, which is sufficient only for purposes of suppressing a behavior, not changing it and (2) the definition of the outcome variable as being reported to the principal’s office, because it might only reflect an increased vigilance by bullies who know they are being targeted. Internal validity limitations amount to incomplete or poor control of important extraneous variables and weaken the logical argument for the study’s findings. External validity limitations refer to the actual population to which the study results can legitimately be generalized. Statistical limitations refer to inadequate or inappropriate statistical conclusions, based on poor choices by the researcher. DIF: Cognitive Level: Analysis 12. Which is the best statement that differentiates between the sizes of samples and populations? a. A sample has a maximum size; a population does not. b. A sample cannot be the same size as a population. c. If a person is a member of a population, he is a member of the sample chosen from

that population. d. A population is usually larger than a sample. ANS: D

The population is the set of all members of a defined group. It contains the elements (humans, animals, plants, events, venues, substances) that share at least one characteristic. In a research study, the population consists of an entire group of people or type of element that represents the focus of the research. A sample is a subset of the accessible population that is selected for a particular study. Being a subset, the sample is either smaller than the population or, very occasionally, equal in size to it; it cannot be larger. DIF: Cognitive Level: Analysis 13. What does a quantitative research instrument measure? a. The level of measurement b. A statistical test c. Itself, for validity d. A study variable ANS: D

Measurement is the process of assigning numbers to objects (or events or situations) in accord with some rule. An instrument is a device selected by the researcher for measurement of a specific variable. DIF: Cognitive Level: Comprehension

14. A researcher believes that adults can remember details about the first time they were taken on

a camping trip, as 7-year-olds, and that the experiences of first camping are life-altering. What is a research term for these beliefs? a. Hypotheses b. Assumptions c. Limitations d. Variables ANS: B

Assumptions are beliefs that are accepted as true, without proof. It is important that researchers make explicit their assumptions related to the conduct of the research. Variables are concrete or abstract ideas that have been made measurable. Hypotheses are stated relationships between or among study variables. Limitations are aspects of the study that decrease the generalizability of the findings. DIF: Cognitive Level: Application 15. Which one of the following items is different, when comparing probability sampling and

nonprobability sampling? a. The type of descriptive statistics applied to the sample b. The size of the sample c. The relative chance of being selected as a study participant d. Whether or not the findings can be generalized ANS: C

Sampling is a process of selecting participants who are representative of the population being studied. The manner in which a sample is chosen determines the degree to which a study’s results are generalizable to the entire population. If a sample represents the population well, the answer to the research question pertains to the entire population. If the sample is not very representative of the population, then the answer to the research question pertains only to the sample or, at best, to only part of the population. Because random sampling methods represent the population well, random sampling allows generalization to a broader slice of the population than does nonrandom sampling. Descriptive statistics may still be applied to either sample and the sample size may be identical. Generalization of the findings is possible under either condition. DIF: Cognitive Level: Analysis 16. A correlational researcher reports that the strength of the relationship between X and Y is near

0 (r = 0.0135). What does this mean, relative to prediction? a. If X is present, Y is only somewhat likely to be present. b. If Y is absent, X will also be absent. c. If X is present, there is no guarantee at all that Y will be present. d. If Y is absent, X will always be present. ANS: C

Correlational analysis allows the researcher to determine the degree or strength of the relationship and the type (positive or negative) of the relationship. A correlation between two variables of –1 is a perfect negative correlation: as one variable increases, the other decreases, and the amount of that increase is completely predictable. A correlation of +1 is a perfect positive correlation: as one variable increases in value, the value of the other variable also increases by a predictable amount. A correlation of 0 signifies no relationship at all. A correlational value near –1 signifies a strong negative relationship, and a value near +1 signifies a strong positive relationship. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. How is a quantitative researcher who exemplifies rigor similar to the best technical nurse who

works in a cardiovascular intensive care unit? (Select all that apply.) a. They both believe in the value of working hard toward a goal. b. They are both aggressive in acquiring and recording data. c. They both strive for excellence. d. They both communicate well with others. e. They both are disciplined in the way they conduct their jobs. f. They both are passionate about accuracy and attending to details. ANS: A, C, E, F

Rigor is the striving for excellence in research, which requires discipline, adherence to detail, consistency, and precision. A rigorously conducted quantitative study has a tightly controlled study design, a representative sample, and precise measuring tools. In rigorous quantitative research, deductions are flawlessly reasoned and decisions are based on the scientific method. The logical reasoning conducted to link the phenomena to be studied at an abstract level to the actual variables and their measurement needs to be meticulous. DIF: Cognitive Level: Synthesis 2. A researcher undertakes a research study on the danger of bears in Yosemite Valley. What

determines the researcher’s selection of a research design? (Select all that apply.) a. The mentor the researcher chooses to support the study b. Whether or not the researcher intends to generalize the findings c. The researcher’s expertise and comfort with the research process chosen d. Whether the National Park Systems are funding the research e. The study purpose and its anticipated outcomes f. The body of research already present on bear danger ANS: B, C, E, F

The research design provides a blueprint for maximizing control over factors that could interfere with a study’s desired outcome. Choice of a design commits the researcher to various details of the research process, which may include number of subject groups, method of sample selection and assignment to group, sample size, type of research setting, whether or not the researcher performs an intervention, timing of the research intervention, duration of the research process, method of data collection, method of data analysis, statistical tests chosen, conclusions able to be drawn from the study results, and scope of recommendations made. Choice of research design may depend, to some extent, upon the researcher’s preferences and prior expertise. DIF: Cognitive Level: Application 3. A researcher selects a quantitative experimental research design. For what reasons does the

researcher select this particular design? (Select all that apply.) a. To generate a theory b. To answer a research question c. To determine which of several causes is the true one d. To prove a theory e. To disprove a hypothesis f. To determine the strength of the relationship between the independent variable and the dependent variable ANS: B, F

The research design provides a blueprint for maximizing control over factors that could interfere with a study’s desired outcome. Choice of a design commits the researcher to various details of the research process, which may include number of subject groups, method of sample selection and assignment to group, sample size, type of research setting, whether or not the researcher performs an intervention, timing of the research intervention, duration of the research process, method of data collection, method of data analysis, statistical tests chosen, conclusions able to be drawn from the study results, and scope of recommendations made. Choice of research design may depend, to some extent, upon the researcher’s preferences and prior expertise. Experimental research tests the null hypothesis by means of applying an intervention to experimental subjects but not to the control subjects, and then measuring the effect on a dependent variable. DIF: Cognitive Level: Application 4. In a given research study, the findings reveal that as A increases, B also increases, that the

relationship is linear, and that the strength of the relationship is 0.78. What type of relationship is this? (Select all that apply.) a. Positive b. Negative c. Inverse d. None e. Causational f. Correlational ANS: A, F

Correlational analysis allows the researcher to determine the degree or strength of the relationship and the type (positive or negative) of the relationship. A correlation between two variables of –1 is a perfect negative correlation: as one variable increases, the other decreases, and the amount of that increase is completely predictable. A correlation of +1 is a perfect positive correlation: as one variable increases in value, the value of the other variable also increases by a predictable amount. A correlation of 0 signifies no relationship at all. A correlational value near –1 signifies a strong negative relationship, and a value near +1 signifies a strong positive relationship. DIF: Cognitive Level: Application 5. A marketing researcher reviews the month’s sales slips for a convenience store, and compares

them with restocking orders, in order to determine which products are being stolen from the shelves. This study has little control. Why is this the case? (Select all that apply.) a. The researcher has no control over whether people choose to shoplift. b. It does not control for extraneous variables. c. No variables are manipulated. d. The design is descriptive or correlational; as compared with other types of research, control is low. e. The data collected were actually generated by other people and may be erroneous. ANS: B, C, D, E

Enacting control of, or controlling for, something refers to researcher actions intended to minimize the effects of extraneous variables. An extraneous variable is something that is not the focus of a study; it has a potential effect on the study, though, making the independent variable appear more or less powerful than it really is in causing a change in the value of the dependent variable. Control for extraneous variables is not an issue for correlational and descriptive research, since attribution of causation is not the goal of the research. DIF: Cognitive Level: Application 6. A researcher conducts a pilot study before the main study is conducted. Why might the

researcher choose to do this? (Select all that apply.) a. The researcher has no idea whether subjects will complete the various phases of the study. b. The researcher needs to know how much of a change will occur in the dependent variable, so that sample size can be determined. c. The researcher isn’t sure whether the fourth phase of the study is really necessary. d. The study site is a new one, and the researcher wants to find out whether it’s suitable for this kind of research. e. The researcher has insufficient funding for a large study. f. The researcher isn’t sure whether the tool used to measure the dependent variable will be practical. g. The researcher doesn’t know whether subject recruitment will be a problem. ANS: A, B, C, D, F, G

A pilot study is a small-scale investigation conducted preparatory to a subsequent adequately powered trial. The purpose of the usual pilot study is to determine whether the proposed methods are effective in locating and consenting subjects, and in collecting useful data. Most pilot studies are feasibility studies. Pilot research can determine whether subjects will actually consent to study participation, how many subjects are really available, how much time is required to gather data on one subject, how well instruments work, whether an intervention produces a measurable difference in the dependent variable, and how large that difference is. In addition, for quantitative studies a statistical analysis of pilot results often is performed, so that the power analysis estimation of the number of subjects needed for statistical significance can be recalculated, assuring an adequate sample. DIF: Cognitive Level: Synthesis 7. What is applied research? (Select all that apply.) a. Research that has been applied in the past to practice b. Research in which the results will be directly useful in clinical practice c. Research usually conducted in the kind of setting in which it will be applied d. Research that is conducted with paid volunteers e. Research conducted to generate knowledge that will directly and indirectly

influence or improve clinical practice ANS: B, C, E

Applied research is a scientific investigation conducted to generate knowledge that is intended to have a direct influence upon practice. DIF: Cognitive Level: Analysis 8. The director of a major hospital complex conducts a study to discover the types of critical

incidents that have occurred in this hospital and its sister hospital over the past 5 years. The director makes a list of every critical incident that has occurred over this period. Choose the true statements about this list. (Select all that apply.) a. The list is the dependent variable. b. The list represents the hospital director’s assumptions. c. The items on the list include every critical incident that has occurred over the past 5 years. d. The sample elements comprise the list. e. If the two hospitals have been in operation only 5 years, the list contains both the sample elements and the accessible population. ANS: D, E

The population is the set of all members of a defined group. It contains the elements (humans, animals, plants, events, venues, substances) that share at least one characteristic. In a research study, the population consists of an entire group of people or type of element that represent the focus of the research. A sample is a subset of the population that is selected for a particular study. Because of error and bias, the list may not include every critical incident that has occurred. It contains every one that the director puts on the list; the director may exclude some and be unaware of others. DIF: Cognitive Level: Application

9. A researcher performs a study of how many nurses are assigned to a nursing floor on the basis

of total square feet of the unit, correlating this with injury, fatigue, patient assignment, patient acuity, and length of employment. Which of the following are true regarding the type of quantitative data analysis used by the researcher? (Select all that apply.) a. The type of quantitative data analysis guides the study objectives and hypotheses. b. The type of quantitative data analysis is determined by the type of data obtained—whether the data are ratio-level or nominal, for instance. c. The type of quantitative data analysis determines the research design. d. The type of quantitative data analysis should include some sort of numerical analysis. e. The kind of data that will be collected is determined by the type of analysis chosen. ANS: B, D

Data analysis is the final step before the study is implemented and should be consistent with the study design. The plans for data analysis are based on (1) research hypotheses or questions and, if these are lacking, research problem and (2) type and volume of data. Most researchers consult a statistician for assistance in developing analysis plans for complex research. Data collected with measurement devices range from the nominal level through the ratio level of measurement. DIF: Cognitive Level: Application

Chapter 04: Introduction to Qualitative Research Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. What does the “grounded” in grounded theory mean? a. Small pieces of data are “ground up” in the analysis process. b. The theory that emerges is “grounded” in real-world data. c. No theory is groundless. d. All data must be “on the ground” and written out fully. ANS: B

Grounded theory research is an inductive research technique developed by Glaser and Strauss through their study of the experience of dying. The method’s name means that the findings are grounded in the concrete world as experienced by participants and grounded in the actual data. The data are interpreted, however, at a more abstract theoretical level. DIF: Cognitive Level: Analysis 2. An ethnographic researcher plans to study organizations and how they promote or suppress

individual effort. What type of ethnography will the researcher select? a. Classical ethnography b. Systematic ethnography c. Interpretive ethnography d. Critical ethnography ANS: B

Four schools of thought within ethnography have emerged from different philosophical perspectives. Classic ethnography seeks to provide a comprehensive description of a culture, usually developed by researchers living for extended periods outside their own country in the environment being studied. In contrast, systematic ethnography explores and describes the structures of the culture with an increased focus on specific groups, institutions, organizations, and patterns of social interaction. Because the study’s scope is limited to a well-defined organizational culture, systematic ethnography is sometimes called focused ethnography. Interpretive ethnography has as its goal understanding the values and thinking that result in behaviors and symbols of the people being studied. Critical ethnography has a political purpose of increasing the awareness of imbalances of power, relieving oppression, and empowering a group of people to take action on their own behalf. DIF: Cognitive Level: Application 3. Why is the Sunrise Model of ethnonursing more specific to health than other ethnography

models? a. It was created by a nurse. b. It values the point of view of the individual. c. It focuses on factors that impact health. d. It explains how various levels of culture interact. ANS: C

Madeline Leininger (1970), who earned her doctoral degree in anthropology, brought ethnography into nursing science by writing the first book linking nursing with anthropology and coining the term ethnonursing. She developed a framework for culture care that became the Sunrise Model. The Sunrise Model identifies factors that affect health and illness, such as religion, income, kinship, education, values, and beliefs. DIF: Cognitive Level: Analysis 4. A researcher investigates the fact that women with chronic pain are more apt to be assessed

and treated for depression than are men with chronic pain, representing a possible inequity of diagnostic delivery, based on gender. Which qualitative strategy will most likely be used to study this topic? a. Grounded theory b. Exploratory-descriptive qualitative research c. Phenomenology d. Critical research ANS: D

Critical ethnography has the political purpose of increasing the awareness of imbalances of power, relieving oppression, and empowering a group of people to take action on their own behalf. Wolf calls this type of ethnography disrupted or disruptive and identifies its philosophical foundation to be critical social theory. Critical theory’s purpose, in general, is to examine the life of a group in the context of an alternative theory or philosophy, such as feminism or constructivism. Critical research designs, such as critical ethnography, have a political purpose of increasing the awareness of imbalances of power, relieving oppression, and/or empowering a group of people to take action on their own behalf. Grounded theory researchers examine experiences and processes with a breadth and depth not usually attainable through quantitative research, generating as complete a description of a phenomenon as is possible. Exploratory-descriptive qualitative studies do not identify an underlying philosophy. Phenomenology describes the lived experience of research participants and has no social agenda. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. A research study about holiday celebrations is based on a philosophy or philosophical

perspective. In the analysis, the authors state that they reflected upon the data for several weeks, reading and rereading interviews, in order to capture their meaning. Aside from descriptive statistics addressing the sample, all the results are presented in narrative form. Which of the following statements are true? (Select all that apply.) a. The philosophy for the study is logical positivism. b. The sample size was decided upon using power analysis. c. In this method, meaning emerges from the data. d. The data analysis process seems to be inductive. e. The method was shaped by the authors’ philosophical perspectives. ANS: C, D, E

Quantitative studies are based primarily on the philosophy of logical positivism. In quantitative research, logic, empirical data, and tightly controlled methods are valued. Power analysis is a quantitative method of setting the sample size. Inductive thinking involves perceptually putting insights and pieces of information together and identifying abstract themes or working from the bottom up. From this inductive process, meanings emerge. In qualitative research, the philosophy directs a researcher’s questions and the collection and interpretation of the data. DIF: Cognitive Level: Application 2. Which statements best describe the differences between Heideggerian and Husserlian

phenomenology? (Select all that apply.) a. Husserl proposed that the researcher could identify and set aside his or her own private attitudes and opinions before data analysis. b. Heidegger postulated that a person interacted with the world only through his or her physical body. c. Heideggerians believe that the past has no influence on present thought. d. Heideggerian phenomenologists posit that the person is situated in a specific context and time that shape his or her experiences, paradoxically freeing and constraining the person’s ability to establish meanings through language, culture, history, purposes, and values. e. Husserl’s enquiry focused on the perception one places on the livid experience, especially on the meaning of that experience. ANS: A, B, D

Husserl articulated the importance of subjectivity, the awareness of one’s own being, feelings, and thoughts that can lead to self-understanding. The person experiencing his or her life must be the one to share the meaning of the experience. To describe the experience, the researcher must be open to the participant’s worldview, set aside personal perspectives, and allow meanings to emerge. Setting aside one’s beliefs during qualitative research is called bracketing. Heideggerian phenomenologists believe that the self exists within a body, or is embodied. Experience cannot occur except through the body and its senses. Emotions and thoughts have physical sensations associated with them. Embodiment implies that the body and mind are intertwined and that there is no such thing as a purely subjective or purely objective world. Building on the idea of embodiment, the person interprets experiences while they are occurring. Because of this, researchers who follow the philosophy proposed by Heidegger do not agree with Husserl’s ideas on bracketing, taking the position that bracketing is not possible. One always remembers and is influenced by what one knows. Heidegger also described situated freedom. A person is situated in specific context and time that shapes one’s experiences, paradoxically freeing and constraining one’s ability to establish meanings through language, culture, history, purposes, and values. Part of an individual’s uniqueness exists because one lives in a historical, cultural, geographic, and temporal context. Martin Heidegger was a student of Husserl but expanded the goal of phenomenology from description of the lived experience to interpretation of the lived experience. DIF: Cognitive Level: Analysis 3. What is exploratory-descriptive qualitative research? (Select all that apply.) a. Research that elicits the perceptions of participants to provide insights for

understanding patients and groups

b. c. d. e.

Quantitative research that contains descriptions Research that contains elements of at least two other types of qualitative research Mixed methods research Studies that are guided by the philosophy of pragmatism with a focus on problem solving

ANS: A, E

Exploratory-descriptive qualitative research elicits the perceptions of participants to provide insights for understanding patients and groups, influencing practice, and developing appropriate programs for specific groups of people. Exploratory- descriptive studies may be guided by the philosophy of pragmatism with a focus on problem solving. DIF: Cognitive Level: Analysis 4. What are the focal points of the four schools of thought within ethnography? (Select all that

apply.) a. To relieve oppression and empower a group to take action on its own behalf b. To investigate cultural structures, focusing on groups and their social patterns c. To construct theories that explain cultural interactions d. To understand values and thinking that collectively result in behaviors and symbols of the individuals within a culture e. To provide a comprehensive holistic description of a culture ANS: A, B, D, E

Four schools of thought within ethnography have emerged from different philosophical perspectives. Classic ethnography seeks to provide a comprehensive description of a culture, usually developed by researchers living for extended periods outside of their own country in the environment being studied. Systematic ethnography (focused ethnography) explores and describes the structures of the culture with an increased focus on specific groups, institutions, organizations, and patterns of social interaction. Interpretive ethnography’s goal is to understand the values and thinking that result in behaviors and symbols of the people being studied: examining implications of behaviors and drawing inferences are the goals of this type of ethnography. Critical ethnography has a political purpose of increasing the awareness of imbalances of power, relieving oppression, and empowering a group of people to take action on their own behalf: its philosophical foundations include critical social theory. It is not ethnography’s goal to generate dense and detailed theory. DIF: Cognitive Level: Synthesis 5. Which of the following are the general purposes of ethnographic research? (Select all that

apply.) a. To describe events within a culture in the distant past b. To describe a culture c. To construct theories that explain cultural interactions d. To measure the effect of living conditions on human care, health, and nursing process e. To explore meanings of social actions against a cultural backdrop f. To travel to other countries or regions in order to expand our understanding of our home culture g. To provide an internal (emic) or external (etic) point of view, or both, about a culture

ANS: B, E, G

Ethnographic research provides a framework for studying cultures. The word ethnography is derived by combining the Greek roots of “ethno” (folk or people) and “graphy” (picture or portrait). Ethnographies are the written reports of a culture from the perspectives of insiders. Initially, ethnographical research was limited to anthropology and the study of primitive, foreign, or remote cultures. Now, however, a number of other disciplines, including social psychology, sociology, political science, education, and nursing, promote cultural research using ethnography. Ethnography does not require travel to another country or region. Ethnography does require spending considerable time in the setting, studying, observing, and gathering data. The insider’s viewpoint is referred to as the emic perspective, as compared to the etic perspective, the views of someone from outside the culture. Participant observation is the primary method of ethnographers and is defined as being present and interacting with participants in routine activities, with the purpose of presenting an emic point of view. Ethnographies are the written reports of a culture from the perspective of insiders. During these interactions, the researcher maintains the etic perspective, noting aspects of shared culture, including behaviors, rules, power structures, customs, and expectations. Historical research describes events in the distant past. DIF: Cognitive Level: Synthesis 6. Which of the following are the general purposes of phenomenological research? (Select all

that apply.) a. To generate theory b. To describe the lived experience c. To observe and document interactions within an existent culture d. To elicit, without judgment, participants’ subjective experiences, in context e. To describe the single reality expressed by a group of participants ANS: B, D

Phenomenology is both a philosophy and a research method. The purpose of phenomenological research is to describe experiences (or phenomena) from the participant perspective or, as frequently stated, capture the “lived experience.” Despite the differences with the philosophical tradition, phenomenologists agree that there is no single reality. Each individual’s experience is unique and ever-changing, according to the person’s array of experiences. Reality is a subjective perception—a tenet that requires the researcher to listen, absorb, and elicit without judgment participants’ subjective experiences in as much detail as possible. The grounded theory research design is used to generate theory. Ethnography is the design of choice for a researcher who seeks to observe and document interactions within an existent culture. DIF: Cognitive Level: Comprehension 7. A certain qualitative mode of enquiry assumes the position that there is no single reality.

Because of this, the reality experienced by each participant is unique. Because experience is subjective, the experienced reality is the subject’s reality. The method does not perform reality checks in order to determine whether a participant’s story is “true” or not. To which ones of the following would these statements pertain? (Select all that apply.) a. Husserlian phenomenology b. Ethnography c. Historicism

d. Heideggerian phenomenology e. Grounded theory ANS: A, D

The purpose of phenomenological research is to describe experiences (or phenomena) as they are lived—in phenomenological terms, to capture the “lived experience” of study participants. All phenomenologists agree that there is not a single reality; each individual has his or her own reality. Reality is considered subjective and, as a result, unique to the individual. Ethnography includes observation and often conversations and interviews with many members of a culture, which ultimately provide the researcher with the “rules” and structure of that culture. An ethnographer compares viewpoints among the research informants, asking questions, so as to clarify the overriding cultural motif. Historicism uses checks and double-checks in order to confirm historical data. Grounded theory uses various strategies by which findings are confirmed by current and subsequent participants, in order to establish shared meanings within a societal group. DIF: Cognitive Level: Analysis 8. What are the general truths of symbolic interaction theory, as utilized in grounded theory

research? (Select all that apply.) a. Perceptions of one’s interactions with others shape one’s self-view. b. Perceptions of one’s interactions with others shape subsequent interactions. c. A person is “embodied” and experiences the world within that body. d. The culture determines behavior; the persons comprise the culture. e. Persons within a social structure share symbols that have meaning for them. ANS: A, B, E

Symbolic interaction theory explores how perceptions of interactions with others shape one’s view of self and subsequent interactions. We cannot completely know the symbolic meanings of another individual; however, individuals in the same group or society may hold common meanings, also called shared meanings. These shared meanings are embedded in catch phrases, beliefs, colloquialisms, and social behaviors, which present a core of belonging. Interactions among people may lead to redefinition of experiences, new meanings, and possibly a redefinition of self. Ethnography studies persons who have a shared culture, and that culture includes behaviors, rules, power structures, customs, and expectations. Heideggerian phenomenologists believe that the self exists within a body, or is embodied. Experience cannot occur except through the body and its senses. DIF: Cognitive Level: Analysis 9. Which of the following are the characteristics of grounded theory research? (Select all that

apply.) a. It focuses on experiences and processes, against the backdrop of society. b. The theory it generates may be tested by subsequent quantitative research. c. It always develops theory. d. It provides as complete a description as possible of a phenomenon of interest. e. It is able to be used effectively only in healthcare settings. ANS: A, B, D

Grounded theory’s name means that the findings are grounded in the concrete world as experienced by participants and grounded in the actual data. When theory is generated by grounded theory research, that theory can serve as a framework for understanding nursing interventions and generating quantitative studies. Grounded theory researchers interpret their results in terms of social processes, using sociology’s symbolic interactionism, developed by George Herbert Mead, as the philosophical underpinning of their worldview. Grounded theory researchers have contributed to our understanding of the patient experience across a wide range of settings. DIF: Cognitive Level: Synthesis

Chapter 05: Research Problem and Purpose Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A researcher has conducted nine clinical studies, some quantitative and others qualitative, all

of which focus on depression’s relationship to perceived abandonment. What is the best description of the phrase “Depression’s relationship to perceived abandonment”? a. Research problem b. Research topic c. Research purpose d. Background statement ANS: B

Research topics are concepts, phenomena of interest, or broad problem areas, such as management of chronic pain that researchers focus on to enhance evidence-based nursing. Research topics contain several potential problems, and each research problem provides the basis for developing many study purposes. The research purpose is the stated reason for conducting a study. Thus, the identification of a relevant research topic and a challenging, significant problem can facilitate the development of numerous study purposes to direct a lifetime program of research. A research problem is an area in which there is a gap in nursing’s knowledge base. DIF: Cognitive Level: Application 2. Why is replicating a research study essential for knowledge development? a. Each time a study is replicated, its probability of error decreases. b. Replicating a study in a different population can decrease generalizability. c. Replication helps confirm that the initial results were not reached in error. d. Replication studies represent the majority of published nursing literature. ANS: C

Replication involves repeating a research study to determine whether its findings are reproducible. Because one or two isolated, small-sample studies do not constitute sufficient evidence on which to base practice, replication of previous research is a respected and essential way to advance the science of nursing, confirming the original study’s results. The reason that replication is so important is that even well-conducted research can produce inaccurate findings. In nursing research, the level of significance typically is set at p <0.05 for the hypothesis testing process. This means that the researcher will allow for a 5% or lower probability of rejecting the null hypothesis when it is indeed true. The probability of error is the same in a replication study as in the original study, if its level of significance is the same. A replication can extend generalizability if the replication study’s population differs from that of the original research. If findings are similar in the replication study, they can then be applied to both populations. Most published nursing research does not consist of replication research. DIF: Cognitive Level: Synthesis

3. A nurse researcher works on a subacute orthopedic hospital floor. The researcher observes

that elder patients with knee replacements sleep as many as 16 hours a day, waking only for physical therapy and meals, but the researcher also notices that those with many visitors sleep fewer hours and seem to experience more pain. The researcher wonders whether sleep in elders after knee replacement prevents pain, or whether elders select the coping strategy of sleeping more, in response to pain, and begins to attempt to identify the relationship between the two. A literature search reveals only three descriptive studies on this general topic, one quantitative and two qualitative, and none of the three explains the relationship between amount of sleep and pain. Which statement is true? a. This is not a researchable problem for a quantitative study: the researcher will not be able to determine the relationship between these concepts. b. This is not a researchable problem for a qualitative study: the ideas in the study will not be able to be expressed by the participants or observed by the researcher. c. This researcher has identified and narrowed the area, reviewed the literature, and identified a problem area. Now a researchable purpose must be identified. d. This topic area is a poor one for the study: with three studies already completed in the area, there is no identifiable research gap. ANS: C

The gap can be one that relates to practice. Because not everything needed for practice is known, many research studies are required to fill this particular gap. There are four steps to deciding on a purpose: identifying one general area that is interesting, imagining at least one general researchable topic within that area, reviewing the literature, and identifying a specific research problem area. Next the researcher will formulate a research purpose. For a quantitative purpose and its related question to be researchable, the concepts or variables to be studied and their relational statement must be tangible, well expressed, and ultimately measurable. For a qualitative purpose and its related question to be researchable, the ideas studied must be able to be expressed by the participants or observed by the researcher. Although three studies have been performed in this area, they all are descriptive and, consequently, do not explore fully the relationship between hours of sleep and pain. DIF: Cognitive Level: Synthesis 4. A master’s student who works in cardiothoracic ICU reads a 20-year-old nursing research

study; the findings document use of much larger per-kilogram amounts of opioids and anxiolytics postoperatively in adults with open-heart surgery, as opposed to children with open-heart surgery. The student strongly suspects that modern hospitals medicate children and adults more or less the same, on a per-kilogram basis. The student decides to replicate the original research in the student’s hospital. What type of replication is this? a. Exact replication b. Concurrent replication c. Systematic replication d. Approximate replication ANS: D

An approximate (or operational) replication is one of the two common replication strategies in nursing. Different researchers conduct the original research, and the replication study adheres to the original design and methods, as closely as possible. The purpose of an approximate replication is to determine whether findings are consistent. Systematic (or constructive) replication, the other common replication strategy in nursing, is conducted under new conditions and its goal is extension of the original study’s findings, most frequently to different settings or to clients with different disease processes. In an exact replication, the replication study is identical to the original and is conducted solely to confirm the original study’s results. An exact, or identical, replication involves duplicating the initial researcher’s study to confirm the original findings. All conditions of the original study must be maintained, including subjects and site. Concurrent (or internal) replication, rare in nursing, is closely related because it uses a different site and, obviously, different subjects, but data collection occurs at the same time in both studies. DIF: Cognitive Level: Application 5. A study contains the research question, “Can the application of twice-daily cortisone in the

period from 6 to 10 weeks postoperatively produce significantly increased range of motion in 50- to 60-year-old rotator-cuff repair patients at the 6-month mark?” What is the type of research described? a. Ethnographic b. Historical c. Experimental d. Basic ANS: C

Both quasi-experimental research and experimental research are conducted to establish evidence for a cause-and-effect relationship: whether the independent variable appears to be effective in causing a change in the dependent variable. This is reflected in the research purpose and in the research question. Within health-related fields, basic researchers seek to increase understanding of physiological or psychological processes by testing hypotheses that can answer general theoretical questions, not specific clinical-based ones; this is a clinical-based question. Ethnographic research examines individuals within cultures, identifying the membership requirements, expected behaviors, enacted behaviors, and rules of the shared culture. Historical research tells a story of the past, from the point of view of persons living in the time that the research was conducted. DIF: Cognitive Level: Synthesis 6. A new disease is identified in the eastern United States. A literature search that shows that no

quantitative research, but only qualitative research, has been performed regarding the disease. The National Institutes of Health (NIH) identifies that same area as one of research priority. What does this collectively describe? a. A research gap b. A purpose statement c. A significance statement d. A feasibility problem ANS: A

A research gap can be one that relates to practice, such as the safest and most efficient way for a community emergency department to triage and establish prompt isolation for a newly identified virus. Because of the scope of what is not known, many research studies are required to fill this particular gap. A second type of gap also may relate to understanding a process related to health, such as hyperactivity. A third type of gap pertains to generating theory, giving the reader insight and understanding of the theory underlying a process. A purpose statement states the reason for conduct of a research study. A significance statement is a justification for the importance of addressing a knowledge gap, be it social, psychological, physiological, cognitive, financial, humanistic, or philosophical. The feasibility of research problem and purpose are determined by access to research subjects and data, availability of sufficient numbers of willing potential subjects, researcher expertise or ability to collaborate with knowledgeable others, financial resources that will cover the costs of the research study, sufficient time for study completion, a manageable-sized purpose, and ethical approval from human subjects committees. DIF: Cognitive Level: Application 7. Which item represents a concise, clear statement of the specific goal or aim of a research

study? a. The research problem was identified as the general area of ignorance surrounding the causation and diagnosis of meningococcal meningitis, especially among soldiers in uniform, and this constituted a significant gap in the literature. b. The purpose of the project, then, was to define changes in the variable of hypertension across time, with the four most prevalent treatment modalities prescribed by primary care physicians in the greater Chicago area. c. The phenomenon of depression experienced by the primary schoolchild was focused upon in this study. It is an under-researched topic, especially since recent research has identified correlational links with childhood obesity, especially in Hispanic and African-American populations. d. Despite the fact that studying the disease, especially from standpoints of prevention and early detection, is costly and time-consuming, it represents a clear priority, since treatment itself is remarkably costly and the afflicted are not likely to experience even short remissions without early intervention. ANS: B

The research purpose is a clear, concise statement of the researcher’s specific focus or aim: the reason the study was performed. A research problem is an area in which there is a gap in nursing’s knowledge base. The words purpose, aim, and objective are used interchangeably in published research. Research topics are broad collections of ideas for potential research projects, related to one phenomenon of interest. Each identified research topic can give rise to many possible research purposes that might be identified. Research topics are broad collections of ideas for potential research projects, related to one phenomenon of interest. Each identified research topic can give rise to many possible research purposes that might be identified. A significance statement is a justification for the importance of addressing this knowledge gap, be it social, psychological, physiological, cognitive, financial, humanistic, or philosophical. DIF: Cognitive Level: Comprehension 8. What is the relationship between a research topic and a research problem?

a. Research topics contain several potential research problems, and each research

problem provides the basis for developing many purposes. b. A research topic is an area in which there is a gap in nursing’s knowledge base. c. The research topic and the research problem are identical. d. The research topic specifies setting and population, but the problem does not. ANS: A

The practice of nursing must be based on knowledge or evidence generated through research. Thus, clinical practice is an extremely important source for research problems that can evolve from clinical observations. For example, while watching the behavior of a patient and family in crisis, you may wonder how you might intervene to improve the family’s coping skills. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. Which of the following are considered evidence-generating? (Select all that apply.) a. Replication of previous research b. Identification of research topics, followed by basic research c. Applied research studies that examine clinical response to interventions d. Reviews of the literature e. Qualitative research examining responses to diagnosis ANS: A, B, C, E

Conducting research generates evidence. Replication involves repeating a research study to determine whether its findings are reproducible. Basic research tests hypotheses and theories in progress, either confirming or refuting them. Applied research in nursing is a scientific investigation conducted to generate knowledge that is intended to have a direct influence upon practice. Qualitative researchers gain insights without measuring concepts or analyzing statistical relationships. Rather, they improve our comprehension of a phenomenon from the viewpoint of the people experiencing it. A review of the literature is conducted to discover the most recent and most important information about a particular phenomenon and to identify any knowledge gaps that exist, but it does not generate evidence. DIF: Cognitive Level: Synthesis

2. Reasons to conduct replication research might include which of the following? (Select all that

apply.) a. The original study, using a small sample, showed statistically significant results. b. The original research showed statistically significant findings, but the research site is no longer in operation. c. The original sample size was adequate, the design was strong, and results showed no statistically significant results. d. Subjects in the original study confided to the researcher, after the research had been completed, that they did not enjoy filling out the survey. e. The original study produced statistically significant results in surgical outpatients. The researcher questioned whether the results would be the same in an inpatient setting. ANS: A, C, E

that focus on its research priorities. A master’s student wants to initiate research to study the relative accuracy of a new computer-assisted assessment device that painlessly measures blood glucose values through a probe just distal to the insertion hub of a central line, in patients on insulin drips with hourly peripheral blood glucose checks. Does this pertain to any of the organization’s research priorities, listed here? (Select all that apply.) a. Effective and appropriate use of technology to achieve optimal patient assessment, management, or outcomes b. Prevention and management of complications c. Processes and systems that foster the optimal contribution of critical care nurses d. Creation of a healing, humane environment e. Effective approaches to symptom management ANS: A, D

The American Association of Critical-Care Nurses (AACN) has determined research priorities for the critical care specialty since the early 1980s and revised these priorities on the basis of patients’ needs and changes in health care. AACN’s (2019) research priorities include: (1) effective and appropriate use of technology to achieve optimal patient assessment, management, and/or outcomes, (2) creation of a healing, humane environment, (3) processes and systems that foster the optimal contribution of critical-care nurses, (4) effective approaches to symptom management, and (5) prevention and management of complications. DIF: Cognitive Level: Synthesis 4. A researcher applying for research funding includes this statement in the proposal: “The

purpose of the research will be, most likely, to document how admirable charitable efforts by The Children of the Land were terminated by the well-meaning Los Angeles Police Force.” What is incorrect about this wording? (Select all that apply.)

a. b. c. d. e.

A police organization cannot be named in a research purpose. A purpose should specify methodology. The terms admirable and well-meaning are both subjective. The purpose must identify the goal of the study, not the “most likely” goal. The purpose should be stated as “was” or “is” but not “will be.”

ANS: C, D, E

The research purpose is the stated reason for conduct of a research study. The purpose statement must be concise and specific if it is to direct the subsequent steps of the research process. In a concise statement, adjectives usually are superfluous. The modifier “most likely” makes it appear that the author is unclear as to the reason for conducting the study. In a research proposal, the purpose statement is couched in the present tense, “The purpose of this research is to investigate ….” and in a research report, in the past tense, “The purpose of this research study was to demonstrate.…” DIF: Cognitive Level: Evaluation 5. A researcher includes the following problem statement in a research proposal: “Children in

publicly funded school breakfast programs often have learning delays. These are not readily attributable to single causes. Research on learning delays has revealed that family literacy, measured by parental reading level and comprehension scores, is the most powerful predictor of delay in the primary grades. On the other hand, repeated exposure to eyes-on reading, in the company of a trusted nonparent adult or peer, has been shown to override family literacy as a predictor. No research, however, has studied institution of a reading-and-breakfast program, delivered 5 days a week before school, intended to override the variable of family literacy.” Given this problem statement, which of these purposes would be appropriate for the study? (Select all that apply.) a. The purpose of the study is to determine whether providing volunteer readers during school breakfasts for all kindergarten and first-grade children will result in fewer than anticipated learning delays. b. The purpose of the study is to determine the lived experience of children with learning delays, against the context of school and home, and to examine the children’s peer relationships. c. The purpose of the study is to determine whether a buddy system of one sixth-grader, and one kindergartner or first-grader, who eat breakfast together and then read together for 20 minutes, is effective in decreasing the anticipated number learning delays. d. The purpose of the study is to experimentally determine what causes learning delays, by introducing various strategies already in place in community primary schools and measuring their effect, using basic research. e. The purpose of the study is to measure the effectiveness of using school computers, allowing children to visually scan a story concurrently read by a schoolteacher over the cafeteria microphone during school breakfast time, in decreasing the incidence and severity of learning delays. ANS: A, C, E

The research purpose is the stated reason for conduct of a research study. The purpose statement must be concise and specific if it is to direct the subsequent steps of the research process. A research problem is an area in which there is a gap in a discipline’s knowledge base. Many research studies may be required to fill one particular gap.

DIF: Cognitive Level: Synthesis 6. In determining a study’s feasibility, which of the following aspects should the novice

researcher consider? (Select all that apply.) a. There is a statistician in the agency with expertise in the data analysis method the researcher has chosen. b. The research problem area is not well researched. The researcher decides that qualitative research is indicated but has no experience in this methodology. c. The community health agency through which the researcher plans to collect data is funded using public dollars. d. The planned outpatient research site treats about 15 persons per month with the disease process that is the focus of study. e. There are three hospitals in town and only one of them is supportive to researchers from outside the institution. f. One of the faculty advisors is very formal and expects students to come to their progress meetings prepared to discuss their work. ANS: A, B, D, E

The feasibility of a study is determine by examining (1) the researcher’s expertise; (2) availability of study participants, facilities, and equipment; (3) time commitment; (4) money commitment; (5) cooperation of others; and (6) the study’s ethical considerations. DIF: Cognitive Level: Application 7. Which of the following research purposes would pertain to quantitative research? (Select all

that apply.) a. The purpose of this study was to identify the stressors and coping strategies of adolescents after a major burn injury. b. The purpose of our study was to establish correlations among panic disorder, bipolar disease, body piercing, and episodes of violence in college freshmen. c. The purpose of this study was to determine the percentage of various types of surgery performed in five hospitals in the Atlanta, Georgia, region. d. The purpose of this study was therefore to explore mothers’ experiences with children who are termed “difficult” toddlers and preschoolers. e. The purpose of this pilot study was to examine the effectiveness of a new, computer-based education module on nurses’ first-attempt mastery of a specialized practice certification examination. ANS: B, C, E

Descriptive research measures prevalence: of a single variable, of the characteristics within populations, of two different variables that may or may not be related, of groups within a population, and so forth. Correlational research measures connections between ideas, and the direction (positive or negative) and strength of those connections. Both quasi-experimental research and experimental research are conducted to establish evidence for a cause-and-effect relationship: whether the independent variable appears to be effective in causing a change in the dependent variable. Phenomenological research investigates participants’ experiences and the meaning those experiences hold for them. Grounded theory research investigates a human process within a sociological focus, and some grounded theory research produces theory. Ethnographic research examines individuals within cultures, identifying the membership requirements, expected behaviors, enacted behaviors, and rules of the shared culture. Historical research tells a story of the past, from the point of view of persons living in the time that the research was conducted. DIF: Cognitive Level: Synthesis 8. A master’s student does not know how to choose a research problem. The student was a

trauma nurse but has not been working clinically for the past 2 years. What sources can the student use in order to identify a researchable nursing problem? Research in the previous work area of trauma nursing does not interest the student. Which of the following activities could be fruitful sources, in identifying a nursing research problem? (Select all that apply.) a. Reading popular magazines to see what kind of research captivates the public’s interest b. Talking with nurses still engaged in clinical practice about questions that have arisen in their work areas c. Reading professional research journals d. Depending on the student’s instructors to provide a research problem e. Accessing the National Institutes for Nursing Research (NINR) research priorities ANS: B, C, E

Rich sources for generating meaningful research are: (1) clinical practice, (2) professional journals in one’s area of expertise, (3) collaboration with faculty and nurse researchers, and (4) research priorities identified by funding agencies and specialty groups. DIF: Cognitive Level: Application 9. What is the relationship among the research problem, the research purpose, and the research

question? (Select all that apply.) a. The purpose is but one of many purposes that can be generated from one particular problem statement. b. The problem statement is more focused and specific than is the purpose. c. The research purpose and the research question should address the same facet of the research problem. d. The problem, purpose, and question are all focused upon a specific gap in the knowledge base. e. Research can be conducted without a research purpose, but not without a research question. ANS: A, C, D

cardiothoracic ICU within a prestigious private hospital, aligned with a teaching institution. A research proposal, concerning ambulation patterns after bypass surgery, is approved by the Human Subjects Committee. Federal funding is obtained. Just before data collection is to begin, the hospital is sold to a large university with a medical school, the nurse manager is replaced with a manager from another hospital in the corporation, and there is a 30% staff turnover. Which of the following factors are expected to affect study feasibility in a negative manner? (Select all that apply.) a. Most of the newly hired nurses are BSNs and newly graduated. b. The new manager grudgingly allows the research to proceed but makes it clear that she will not support subsequent research until the unit is more stable. c. Fewer patients come to this hospital now for bypass surgery, going instead to its sister hospital across town. d. Two of the research assistants, who were already trained, take jobs elsewhere. e. Staff nurses disliked the old manager and like the replacement one. ANS: B, C, D

If site access is granted only grudgingly, the researcher must assess the extent to which the agency will cooperate with the researcher. An unwilling manager, or unwilling staff, can make data collection difficult. In addition, access to adequate numbers of subjects is crucial. Nurses with a Bachelor of Science in Nursing (BSN) degree have knowledge of the research process and might provide valuable assistance in identifying research problems and collecting data for studies. Because the research assistants are leaving, the researcher must now assume their tasks, until others are hired. DIF: Cognitive Level: Analysis 11. Which of the following research purposes would pertain to qualitative research? (Select all

that apply.) a. The purpose of this study was to explore the lived experience of work in a bone marrow transplant unit. b. The purpose of our research was to establish evidence for the financial value to the institution of employing clinical nurse specialists, in terms of outcomes. c. The purpose of this study was to examine the culture of working mothers and their balancing act of home and work commitments. d. The purpose of this study was to test the associations among pet ownership, community social engagement, personal friendships, and family relationships. e. The purpose of this study was to determine the effectiveness of beta blockers in the management of heart failure in older adults. ANS: B, C

Phenomenological research investigates participants’ experiences and the meaning those experiences hold for them. Grounded theory research investigates a human process within a sociological focus, and some grounded theory research produces theory. Ethnographic research examines individuals within cultures, identifying the membership requirements, expected behaviors, enacted behaviors, and rules of the shared culture. Descriptive research measures prevalence: of a single variable, of the characteristics within populations, of two different variables that may or may not be related, of groups within a population, and so forth. Correlational research measures connections between ideas, and the direction (positive or negative) and strength of those connections. Both quasi-experimental research and experimental research are conducted to establish evidence for a cause-and-effect relationship: whether the independent variable appears to be effective in causing a change in the dependent variable. DIF: Cognitive Level: Synthesis

Chapter 06: Objectives, Questions, Hypotheses, and Study Variables Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A pediatric nurse, who has worked on the inpatient unit for 7 years, is enrolled in a master’s

program. The nurse notes that children who are homeless and who are admitted to the inpatient setting seem to have longer lengths of hospital stay, appear to have poorer verbal skills, and seem to be more fearful of separation from their parents. The nurse designs a study to measure these variables in homeless children and to compare the findings with the average patients on the same unit. What is the research objective? a. To answer the research question b. To determine the strength of the statistical relationship among the variables c. To determine whether homeless children seem to have longer length of hospital stay, poorer verbal skills, and more fear of separation from their parents than do other children d. To measure length of stay, verbal skills, and fear of separation from parents in homeless children admitted to the hospital ANS: C

Research objectives or aims are clear, concise, declarative statements expressed in the present tense to specify the foci of the study—that is, the reasons for performing the study. There are minimal if any differences between the terms objective and aim, thus researchers use them interchangeably in studies. Some researchers identify their study purpose as an objective or aim, which can be confusing to readers. The purpose is the overall focus on the study, and smaller foci of the study are identified in the research objectives/aims or questions. DIF: Cognitive Level: Synthesis 2. A pediatric nurse, who has worked on the inpatient unit for 7 years, is enrolled in a master’s

program. The nurse notes that children who are homeless and who are admitted to the inpatient setting seem to have longer lengths of hospital stay, appear to have poorer verbal skills, and seem to be more fearful of separation from their parents. The nurse designs a study to measure these variables in homeless children, and to compare the findings with the average patients on the same unit. What is the research question? a. Are longer hospital stays, poorer verbal skills, and increased fear of separation from parents made worse by children’s homelessness? b. Does children’s homelessness affect length of hospital stay, verbal skills, and fear of separation from parents? c. Was homelessness related to length of hospital stay, verbal skills, and fear of separation from parents in this study? d. Is homelessness in children related to length of hospital stay, verbal skills, and fear of separation from parents? ANS: D

A research question is a concise, interrogative statement that is worded in the present tense and includes one or more of a study’s principal concepts. Research questions are actual queries that address variables, and sometimes the relationships among them, within a population. In this case, the examination of relationships among variables, would be the focus of the research question, since cause is not a focus of study. DIF: Cognitive Level: Application 3. A pediatric nurse, who has worked on the inpatient unit for 7 years, is enrolled in a master’s

program. The nurse notes that children who are homeless and who are admitted to the inpatient setting seem to have longer lengths of hospital stay, appear to have poorer verbal skills, and seem to be more fearful of separation from their parents. The nurse designs a study to measure these variables in homeless children, and to compare the findings with the average patients on the same unit. What is the research hypothesis? a. Longer length of hospital stay, worse verbal skills, and fear of separation from parents are caused by children’s homelessness. b. Homelessness in children is related to length of hospital stay, verbal skills, and fear of separation from parents. c. There is no relationship between children’s homelessness and length of hospital stay, verbal skills, and fear of separation from parents. d. If a homeless child has a longer hospital stay, that child is likely to have poor verbal skills and more difficulty separating from parents. ANS: B

A hypothesis is a stated relationship between or among variables, within a specified population. It uses the same variables originally identified as concepts in the research purpose and subsequently given operational definitions. It uses the same population identified in the purpose and research question. It uses the same relationships identified in the purpose and question, if a relationship is stated, focusing on the association between variables if the research is correlational, or on causation if one variable is proposed to cause another. Hypotheses are described using the terms in the following four categories: (1) causal versus associative, (2) simple versus complex, (3) directional versus nondirectional, and (4) null versus research. DIF: Cognitive Level: Application 4. A researcher identifies three variables and formulates a hypothesis that links them. That

hypothesis is testable. What does it mean that the hypothesis is testable? a. All the variables in the hypothesis are measurable. b. The hypothesis must be replaced by a research question. c. The value of the hypothesis is low. d. The hypothesis is causational. ANS: A

A testable hypothesis contains variables that can be precisely measured or manipulated in a study. Formulating a testable hypothesis to guide a study requires several decisions. The research problem and purpose determine whether you will study an associative or a causal relationship. Testing a hypothesis that states a causal relationship requires expertise in implementing an intervention and controlling extraneous variables. You must also decide whether the research problem and purpose are best investigated with the used of simple or complex hypotheses. Another decision you must make involves the formulation of a research or a null hypothesis based on the most current knowledge of the research problem. DIF: Cognitive Level: Synthesis 5. A professor of medical-surgical nursing researches the effect of special tutoring sessions

offered once weekly to students, in hopes of improving student performance on examinations. In the fall semester, student exam scores were significantly improved over those of the previous term, when tutoring was not offered. The performance of the spring term students does not show a significant improvement over students without tutoring. The professor’s colleague identifies a confounding variable. Which variable is the confounding variable? a. The same professor provided tutoring in both fall and spring semesters. b. The fall semester students had a lower admission grade point average than the spring semester students. c. The fall semester students were, on average, older than the spring students. d. The fall tutoring sessions were conducted on Mondays after the medical-surgical class and the spring sessions were held on Fridays, after a different class. ANS: D

A confounding variable is a special subtype of extraneous variable, but it is unique in that it is embedded in the study design because it is intertwined with the independent variable. In this example, the day of the week on which tutorials were offered might have made a difference in effectiveness. Confounding variables cannot be controlled for, once the study is under way. Modifying variables, when present, are those that change the strength and sometimes the direction of a relationship between other variables. Mediating variables are intermediate variables that occur as links in the chain between independent and dependent variables. Environmental variables are those that emanate from the research setting. In a healthcare milieu, they include but are not limited to temperature, ambient noise, lighting, rules regulating the length of nurses’ breaks, floor surface covering, actions of other clients, and furniture. DIF: Cognitive Level: Application 6. The intervention that the researcher manipulates is the: a. demographic variable. b. independent variable. c. dependent variable. d. extraneous variable. ANS: B

The independent variable is the intervention or treatment that the researcher applies to the experimental group but not to the control group. Demographic variables are subject characteristics measured during a study and used to describe a sample. In nursing research, common demographic variables are age, gender, and ethnicity, which define the population represented by the sample. The dependent variable is so called because it depends on the action of the independent variable. The dependent variable is defined as the result or outcome that is the study’s focus. Extraneous variables are variables that are not central to a study’s research purpose: they are not identified as either independent or dependent variables. An extraneous variable has a potential effect on the results, however, making the independent variable appear more or less powerful than it really is in its effect on the value of the dependent variable. DIF: Cognitive Level: Comprehension 7. A researcher identifies an important extraneous variable after a study is under way. What is

the best action for the researcher to take now? a. Determine whether the extraneous variable is an independent or dependent variable. b. Stop the study, then redesign it so as to control for this extraneous variable. c. Attempt to measure the extraneous variable so that its effect may be determined during the analytic phase. d. Nothing now. Plan to identify this as a limitation during the dissemination phase. ANS: B

Extraneous variables are variables that are not central to a study’s research purpose: they are not identified as either independent or dependent variables. An extraneous variable has a potential effect on the results, however, making the independent variable appear more or less powerful than it really is in its effect on the value of the dependent variable. When conducting a study, the researcher should attempt to identify potentially extraneous variables that might have an effect on study’s findings. The researcher may then make adjustments in the research design and methods in order to attempt to control for the intrusion of only the extraneous variables that are most likely to alter the research findings and consequently force an incorrect conclusion. DIF: Cognitive Level: Analysis 8. Simple descriptive statistics may be used to depict the sample characteristics, reflecting

demographic variable values, in which kind of research? a. Quantitative research only b. Qualitative research only c. Both quantitative and qualitative research d. Only when data have been extracted from an electronic database ANS: C

Demographic variables are participant characteristics measured during a study and used to describe a sample. In nursing research, common demographic variables are age, gender, and ethnicity, which define the population represented by the sample. After study completion, demographic information is analyzed to provide what are called the sample characteristics, or occasionally the sample demographics. Sample characteristics are presented narratively at the beginning of the results section, in both quantitative and qualitative research. They are often displayed in table form, as well, using simple descriptive statistics such as frequency and percentage, in quantitative research and occasionally in qualitative research. DIF: Cognitive Level: Application 9. A research hypothesis states: “Patients with recurrent bowel obstruction due to Crohn’s

disease who are assigned to be treated in an emergency room complain less frequently of pain and require less pain medication than those patients admitted, in the usual fashion, and treated on a medical floor.” What is the independent variable in the hypothesis? a. Bowel obstruction due to Crohn’s disease b. Place treated c. Number of complaints of pain d. Number of doses of pain medication ANS: B

An independent variable is either a cause or a predictor, depending on the research design. A dependent variable is the entity that it is the researcher’s intent to produce, modify, or predict. DIF: Cognitive Level: Application 10. Read the following purpose statement: “The purpose of this study was to examine the effects

of a generous weekly allowance and twice-weekly text messages from parents on number of days absent from class, in freshman college students.” What kind of variable is number of days absent from class? a. Demographic variable b. Independent variable c. Extraneous variable d. Dependent variable ANS: D

A dependent variable is the entity that it is the researcher’s intent to produce, modify, or predict. The dependent variable is defined as the result or outcome that is the study’s focus. Demographic variables are subject characteristics measured during a study and used to describe a sample. In nursing research, common demographic variables are age, gender, and ethnicity, which define the population represented by the sample. So an independent variable is either a cause or a predictor, depending on the research design. Extraneous variables are variables that are not central to a study’s research purpose: they are not identified as either independent or dependent variables. An extraneous variable has a potential effect on the results, however, making the independent variable appear more or less powerful than it really is in its effect on the value of the dependent variable. DIF: Cognitive Level: Application

11. Read the following statement: There is no measurable difference in incidence of incarceration

for adolescent children whose mothers work outside the home in comparison with those whose mothers do not work outside the home. How is this statement best defined? a. Null hypothesis b. Confounding variable c. Research objective d. Research question ANS: A

A hypothesis is a stated relationship between or among variables, within a specified population. The null hypothesis, also referred to as a statistical hypothesis, is used for statistical testing and interpretation of statistical outcomes. The null hypothesis can be simple or complex and associative or causal. The null hypothesis states that there is no relationship between two or more variables. A confounding variable is a special subtype of extraneous variable, but it is unique in that it is embedded in the study design because it is intertwined with the independent variable. Objectives or aims in quantitative studies are developed on the basis of the research problem and purpose, in order to clarify a study’s goals. The objectives or aims use the same major variables identified in the purpose statement and examine these within the same population. Research objectives are clear, concise, declarative statements that are expressed in the present tense, focus on one or two variables (or concepts), and indicate whether the variables are to be identified or described. A research question is a concise, interrogative statement that is worded in the present tense and includes one or more of a study’s principal concepts. DIF: Cognitive Level: Application 12. A research hypothesis states: “There is no measurable difference in incidence of acne in

15-year-olds who are placed on a chocolate-free diet.” What is the dependent variable in this hypothesis? a. 15-year-olds b. No chocolate in the diet c. Chocolate in the diet d. Acne ANS: D

The independent variable is the intervention or treatment that the researcher applies to the experimental group but not to the control group. The dependent variable is so called because it depends on the action of the independent variable. The dependent variable is defined as the result or outcome that is the study’s focus. Extraneous variables are variables that are not central to a study’s research purpose: they are not identified as either independent or dependent variables. In this example, acne is the dependent variable and removal of chocolate from the diet is the independent variable. DIF: Cognitive Level: Application 13. What is the relationship between a conceptual definition and an operational definition? a. The conceptual definition provides information; the operational definition provides

none. b. The conceptual definition is concrete, and the operational definition is abstract. c. They are the same, in most instances. d. The operational definition allows the researcher to create a measurable variable

from a concept; the conceptual definition does not. ANS: D

In quantitative studies, a variable can be defined both conceptually and operationally, revealing both its meaning and its means of measurement in a particular study. Operationally defining a concept converts it to a variable and provides a definition of how the researcher will quantify that variable during the course of a study. DIF: Cognitive Level: Analysis 14. The research question states: “Can diabetics on oral antiglycemic medications achieve better

control of blood sugar, as measured by Hemoglobin A1C, if they are taught to meditate and do this on a daily basis?” What is the independent variable in this research question? a. Oral antiglycemic medications b. Hemoglobin A1C c. Meditation d. Blood sugar ANS: C

The independent variable is the intervention or treatment that the researcher applies to the experimental group but not to the control group. The dependent variable is so called because it depends on the action of the independent variable. The dependent variable is defined as the result or outcome that is the study’s focus. Extraneous variables are variables that are not central to a study’s research purpose: they are not identified as either independent or dependent variables. In this example, Hemoglobin A1C is the dependent variable and meditation is the independent variable. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. A pediatric nurse, who has worked on the inpatient unit for 7 years, is enrolled in a master’s

program. The nurse notes that children who are homeless and who are admitted to the inpatient setting have longer lengths of hospital stay, appear to have poorer verbal skills, and seem to be more fearful of separation from their parents. The nurse designs a study to measure these variables in homeless children and to compare the findings with the average patients on the same unit. What are the research variables in this study? (Select all that apply.) a. Patient age b. Verbal skills c. Homelessness d. Parental presence e. Fear of separation from parents f. Length of hospital stay ANS: B, C, E, F

Research variable is a default term used to refer to a variable that is the focus of a quantitative study but that is not identified as an independent or a dependent variable. Research variables include those stated in the research purpose and question. DIF: Cognitive Level: Application

2. A research hypothesis states: “Having one’s house and yard professionally sprayed yearly by

an extermination service has an effect on infestations of common garden ants.” What type of hypothesis is this? (Select all that apply.) a. Simple hypothesis b. Complex hypothesis c. Causal hypothesis d. Associative hypothesis e. Nondirectional hypothesis f. Directional hypothesis ANS: A, C, E

A simple hypothesis predicts the relationship (associative or causal) between two variables. A complex hypothesis predicts the relationship (associative or causal) among three or more variables. The relationships identified in hypotheses are associative or causal. A causal hypothesis proposes a cause-and-effect relationship between variables, in which one causes the other. The cause is the independent variable; the result is the dependent variable. An associative hypothesis presents a noncausative relationship between or among variables. A nondirectional hypothesis states that a relationship exists but does not specify the direction of the relationship. A directional hypothesis states the nature or direction of a proposed relationship between variables. DIF: Cognitive Level: Analysis 3. A research hypothesis states: “Providing early written feedback to undergraduate nursing

students in the clinical setting increases the incidence of desired behaviors of safe medication administration, work efficiency, accurate charting, and competent time management.” What type of hypothesis is this? (Select all that apply.) a. Simple hypothesis b. Complex hypothesis c. Causal hypothesis d. Associative hypothesis e. Nondirectional hypothesis f. Directional hypothesis ANS: B, C, F

A simple hypothesis predicts the relationship (associative or causal) between two variables. A complex hypothesis predicts the relationship (associative or causal) among three or more variables. The relationships identified in hypotheses are associative or causal. A causal hypothesis proposes a cause-and-effect relationship between variables, in which one causes the other. The cause is the independent variable; the result is the dependent variable. An associative hypothesis presents a noncausative relationship between or among variables. A nondirectional hypothesis states that a relationship exists but does not specify the direction of the relationship. A directional hypothesis states the nature or direction of a proposed relationship between variables. DIF: Cognitive Level: Analysis 4. A research hypothesis states: “Number of hours spent daily playing videogames is negatively

related to student achievement in high school history class.” What type of hypothesis is this? (Select all that apply.) a. Simple hypothesis

b. c. d. e. f.

Complex hypothesis Causal hypothesis Associative hypothesis Nondirectional hypothesis Directional hypothesis

ANS: A, D, F

A simple hypothesis predicts the relationship (associative or causal) between two variables. A complex hypothesis predicts the relationship (associative or causal) among three or more variables. The relationships identified in hypotheses are associative or causal. A causal hypothesis proposes a cause-and-effect relationship between variables, in which one causes the other. The cause is the independent variable; the result is the dependent variable. An associative hypothesis presents a noncausative relationship between or among variables. A nondirectional hypothesis states that a relationship exists but does not specify the direction of the relationship. A directional hypothesis states the nature or direction of a proposed relationship between variables. DIF: Cognitive Level: Analysis 5. A research hypothesis states: “The number of minutes a 16-year-old girl spends applying her

makeup in the morning is related to her perceived personal attractiveness.” What type of hypothesis is this? (Select all that apply.) a. Simple hypothesis b. Complex hypothesis c. Causal hypothesis d. Associative hypothesis e. Nondirectional hypothesis f. Directional hypothesis ANS: A, D, E

A simple hypothesis predicts the relationship (associative or causal) between two variables. A complex hypothesis predicts the relationship (associative or causal) among three or more variables. The relationships identified in hypotheses are associative or causal. A causal hypothesis proposes a cause-and-effect relationship between variables, in which one causes the other. The cause is the independent variable; the result is the dependent variable. An associative hypothesis presents a noncausative relationship between or among variables. A nondirectional hypothesis states that a relationship exists but does not specify the direction of the relationship. A directional hypothesis states the nature or direction of a proposed relationship between variables. DIF: Cognitive Level: Analysis 6. A research hypothesis states: “Decreasing the time allotted for weekly, in-class pop quizzes

increases student anxiety and decreases student grades.” What type of hypothesis is this? (Select all that apply.) a. Simple hypothesis b. Complex hypothesis c. Causal hypothesis d. Associative hypothesis e. Nondirectional hypothesis f. Directional hypothesis

ANS: B, C, F

A simple hypothesis predicts the relationship (associative or causal) between two variables. A complex hypothesis predicts the relationship (associative or causal) among three or more variables. The relationships identified in hypotheses are associative or causal. A causal hypothesis proposes a cause-and-effect relationship between variables, in which one causes the other. The cause is the independent variable; the result is the dependent variable. An associative hypothesis presents a noncausative relationship between or among variables. A nondirectional hypothesis states that a relationship exists but does not specify the direction of the relationship. A directional hypothesis states the nature or direction of a proposed relationship between variables. DIF: Cognitive Level: Analysis 7. A research hypothesis states: “The number of children in the home is associated with noise

level in that home and with parental stress.” What type of hypothesis is this? (Select all that apply.) a. Simple hypothesis b. Complex hypothesis c. Causal hypothesis d. Associative hypothesis e. Nondirectional hypothesis f. Directional hypothesis ANS: B, D, E

A simple hypothesis predicts the relationship (associative or causal) between two variables. A complex hypothesis predicts the relationship (associative or causal) among three or more variables. The relationships identified in hypotheses are associative or causal. A causal hypothesis proposes a cause-and-effect relationship between variables, in which one causes the other. The cause is the independent variable; the result is the dependent variable. An associative hypothesis presents a noncausative relationship between or among variables. A nondirectional hypothesis states that a relationship exists but does not specify the direction of the relationship. A directional hypothesis states the nature or direction of a proposed relationship between variables. DIF: Cognitive Level: Analysis 8. A research hypothesis states: “Increased intake of dietary fiber in elders and increased fluid

intake are associated with fewer episodes of diverticulitis.” What type of hypothesis is this? (Select all that apply.) a. Simple hypothesis b. Complex hypothesis c. Causal hypothesis d. Associative hypothesis e. Nondirectional hypothesis f. Directional hypothesis ANS: B, D, F

A simple hypothesis predicts the relationship (associative or causal) between two variables. A complex hypothesis predicts the relationship (associative or causal) among three or more variables. The relationships identified in hypotheses are associative or causal. A causal hypothesis proposes a cause-and-effect relationship between variables, in which one causes the other. The cause is the independent variable; the result is the dependent variable. An associative hypothesis presents a noncausative relationship between or among variables. A nondirectional hypothesis states that a relationship exists but does not specify the direction of the relationship. A directional hypothesis states the nature or direction of a proposed relationship between variables. DIF: Cognitive Level: Analysis 9. A research hypothesis states: “Taking lessons to learn how to play bridge and weekly practice

in playing bridge have an effect on beginning bridge players’ win-loss ratio.” What type of hypothesis is this? (Select all that apply.) a. Simple hypothesis b. Complex hypothesis c. Causal hypothesis d. Associative hypothesis e. Nondirectional hypothesis f. Directional hypothesis ANS: B, C, E

A simple hypothesis predicts the relationship (associative or causal) between two variables. A complex hypothesis predicts the relationship (associative or causal) among three or more variables. The relationships identified in hypotheses are associative or causal. A causal hypothesis proposes a cause-and-effect relationship between variables, in which one causes the other. The cause is the independent variable; the result is the dependent variable. An associative hypothesis presents a noncausative relationship between or among variables. A nondirectional hypothesis states that a relationship exists but does not specify the direction of the relationship. A directional hypothesis states the nature or direction of a proposed relationship between variables. DIF: Cognitive Level: Analysis 10. An experimental psychologist studies rat behavior. The psychologist runs rats through a maze,

under different scent conditions. At the end of the maze is cheese. Sometimes the maze is lit, and sometimes it is dark. During each run, the rats are subjected to different scents (cat pheromone, the smell of cheddar cheese, tiger pheromone, the smell of rat feces) at crucial decision points in the maze. The psychologist measures the time it takes the rats to finish the maze. What could be considered independent variables in this study? (Select all that apply.) a. The rats b. Light versus dark c. The psychologist d. The amount of time the rats take to finish the maze e. The scents f. The cheese at the end of the maze g. Rat behavior ANS: B, E

The independent variable is the intervention or treatment that the researcher applies to the experimental group but not to the control group. The dependent variable is so called because it depends on the action of the independent variable. The dependent variable is defined as the result or outcome that is the study’s focus. In this example, how long it takes the rats to run through the maze is the dependent variable and different scents are independent variables; light versus dark are the two experimental conditions, and these could also affect the outcome, so they could also be considered independent variables. DIF: Cognitive Level: Application 11. A cook wants to know what happens to bacon when it is fried in a frying pan, versus

microwaving it. Specifically, the cook wonders if the bacon ends up moister and more flavorful when fried or when microwaved. What are the dependent variables? (Select all that apply.) a. Frying bacon b. Microwaving bacon c. Consistent cooking temperature d. Variable cooking temperature e. Moistness of bacon f. Kitchen burns g. Flavor of bacon ANS: E, G

The independent variable is the intervention or treatment that the researcher applies to the experimental group but not to the control group. The dependent variable is so called because it depends on the action of the independent variable. The dependent variable is defined as the result or outcome that is the study’s focus. In this example, the moistness and flavor of bacon are the dependent variables and the method of cooking is the independent variable. DIF: Cognitive Level: Application 12. Which could be a research question? (Select all that apply.) a. What does postoperative vomiting feel like, to research subjects? b. How is hypnosis related to smoking cessation? c. In an English course, how do grading, praise, practice, submitting papers for

publication, and writing skills interact? d. What are the differences between clients with preoperative orientation and those

without, in terms of procedural anxiety? e. How does the researcher define loneliness? ANS: A, B, C, D

A research question is a concise, interrogative statement that is worded in the present tense and includes one or more of a study’s principal concepts. Research questions are actual queries that address variables, and sometimes the relationships among them, within a population. DIF: Cognitive Level: Application 13. What could be an independent variable in an experimental study? (Select all that apply.) a. Quality of life b. The percentage of moisture in the inspired air the subject breathes

c. The researcher’s preference for quantitative versus qualitative methodologies d. Wearing a hat with a large brim e. Seizure activity during the experiment ANS: B, D

The independent variable is the intervention or treatment that the researcher applies to the experimental group but not to the control group. The dependent variable is so called because it depends on the action of the independent variable. The dependent variable is defined as the result or outcome that is the study’s focus. DIF: Cognitive Level: Analysis 14. What could be a dependent variable in an experimental study? (Select all that apply.) a. Medication A b. The number of times the gerbil rings the bell c. Quality of life d. The number of times the subject is instructed in how to use the experimental

equipment e. Vomiting ANS: B, C, E

Chapter 07: Review of Relevant Literature Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. Which study would be considered landmark research? a. The discovery that during pancreatitis, the pancreas is actually digested by its own

enzymes b. A description of the importance of injecting immunizations in the proper location

of the deltoid c. The third in a series of four papers describing patterns of emergency room use in

vacation communities d. The first paper describing the effect of using insulin for type I diabetes in humans ANS: D

Landmark studies are published research that lead to an important development or a turning point in a certain field of study. DIF: Cognitive Level: Application 2. A publication is printed every 2 months. Its volume number coincides with its year of

publication (2008 = 1; 2009 = 2; 2010 = 3; etc.). Its issue number coincides with the order of publication, within a given year (Jan to Feb = 1; Mar to Apr = 2; etc.). What kind of a publication is this? a. A monograph b. A periodical c. An eBook d. A serial ANS: B

Serials are published over time or may be published in multiple volumes at one time, but do not necessarily have recurrent and predictable publication dates. Periodicals are subsets of serials with predictable publication dates, such as journals. Periodicals are published over time and are numbered sequentially. This sequential numbering is seen in the year, volume, issue, and page numbering of a journal. Monographs, such as books, hard-copy conference proceedings, and pamphlets, are written and published for a specific purpose and may be updated with a new edition, as needed. Textbooks are monographs written as resource materials for education programs. Many books and textbooks are now available in a digital format known as eBooks. DIF: Cognitive Level: Application 3. What type of literature describes concept analyses, models, and frameworks? a. Empirical b. Applicable c. Able to be replicated d. Theoretical ANS: D

Theoretical literature consists of concept analyses, models, theories, and conceptual frameworks that support a selected research problem and purpose. Empirical literature is comprised of knowledge derived from research. DIF: Cognitive Level: Comprehension 4. Which primary source might be available to someone writing a biography of Queen Elizabeth

I, who died in the 17th century? a. An interview with one of her maids-in-waiting b. A previous history written about her c. An article about her in a 17th-century publication d. A diary written by her ANS: D

The published literature contains primary and secondary sources. A primary source is written by the person who originated, or is responsible for generating, the ideas published. A secondary source summarizes or quotes content from primary sources. Thus, authors of secondary sources interpret the works of researchers and theorists, paraphrase the information, and cite the information in their papers. DIF: Cognitive Level: Application 5. What is the purpose of the minimal review of relevant studies that the grounded theory

researcher undertakes before writing the research proposal? a. To compare the anticipated findings with the findings of similar research b. To direct the researcher in how to strategize data collection c. To help the researcher to identify previous findings that will assist in interpretation of the planned study d. To reveal the need for the planned research by identifying what others have done ANS: D

In qualitative research, the purpose and timing of the literature review vary based on the type of study to be conducted. Classical grounded theory researchers begin with “tabula rasa,” a blank slate, an attempt to know as little as possible about the area of study before they begin the research, so the only point of the perusal of the brief literature overview performed prior to enactment of the study is to discover whether this particular study has been performed before. As the process progresses, the researchers collect and analyze all data before they return to the literature, so that the entirety of the analysis is grounded in their data, not in the literature. When the core concept or process has been identified and data analysis is complete, the researcher theoretically samples the literature for extant theories that may assist in explaining and extending the emerging theory. DIF: Cognitive Level: Application 6. In terms of the literature review, how are quantitative research and ethnographic research

similar? a. Both require the researcher to review the literature before beginning the study. b. Both require the researcher to review the literature after completion of data analysis. c. Both require the researcher to utilize the literature as the primary data source. d. Both consider the literature review extraneous, postponing it until after the study is

published. ANS: A

In qualitative research, the purpose and timing of the literature review vary based on the type of study to be conducted. The role of the literature review for ethnographic research is similar to role of the literature review for quantitative research. The ethnographic researcher is expected to prepare extensively before data collection, in order to become familiar with the culture, and this includes detailed review of the literature. The literature review provides a background for conducting the study and interpreting the findings. DIF: Cognitive Level: Analysis 7. Considering phenomenologists’ belief that experience constitutes reality, how does their

approach to the literature review dovetail with that belief? a. The literature is exactly as real as the other research data, and it is all analyzed and valued equally during the data analysis portion of the study. b. If the literature reports other phenomenologists’ findings, based on experience, these can be considered alternative data sources. c. The literature is a false interpretation of reality and cannot be considered, either before or after data analysis is complete. d. The literature review is usually postponed until after data analysis completion, so that the understanding of the phenomenon will emanate solely from the data. ANS: D

search of journals on the topic of prolonged adolescent grieving after parental loss? a. It focuses the search on parental loss, the last search term. b. It is useful when a researcher is undecided. c. It narrows the search to articles containing all terms. d. It allows the researcher to enter synonymous terms such as parental loss and parental death, instructing the computer to find articles containing either term. ANS: D

The Boolean operators are the three words AND, OR, and NOT. In most search engines the words must be capitalized for them to function in this way. The Boolean operator AND is used to search for the presence of two or more terms in the same citation. The Boolean operator OR is most useful with synonymous terms or concepts, such as compliance and adherence. It is used to search for the presence of either of two terms in the same search. The Boolean operator NOT is used to search for one idea but not another in the same citation. NOT is used less frequently because doing so may result in missing relevant publications. DIF: Cognitive Level: Application

9. The original quotation in the fictional text by Atchison, Topeka, and Santa Fe (2009) is as

follows: “Because of overemphasis on academic excellence, especially test grades, the high schools studied had a disproportionate number of students who reported sleeplessness, nervousness, nightmares, and guilt. These were attributed to various factors, the most significant of which was a very strict principal, who voiced open disapproval of students she felt were underachieving their enormous academic potential. Parents were very accepting of this behavior, echoing it in their interactions with the students.” What is the acceptable way to properly attribute this content in a literature review? a. Parents were very accepting of the principal’s behavior, which included voiced disapproval of underachieving students, echoing it in their interactions with their sons and daughters. b. Because of overemphasis on academic excellence, especially test grades, the high schools studied had a disproportionate number of students who reported sleeplessness, nervousness, nightmares, and guilt. These were attributed to various factors, the most significant of which was a very strict principal, who voiced open disapproval of students she felt were underachieving their enormous academic potential. Parents were very accepting of this behavior, echoing it in their interactions with the students (Atchison, Topeka, & Santa Fe, 2009). c. As compared with other high schools, Atchison et al. (2009) reported a higher incidence of distress manifestations, such as nightmares and nervousness, in a strictly college-prep school with an extremely disapproving principal, who verbally berated students for less-than-expected academic performance. d. High schools with disapproving authority figures have a higher incidence of somatization (see Atchison et al., 2009). ANS: C

Citation is the act of quoting or paraphrasing a source within the body of a paper, using it as an example, or presenting it as support for a position taken. Rather than using direct quotes from an author, the writer of the literature review should paraphrase the author’s ideas. Paraphrasing involves expressing the ideas clearly and in one’s own words; the ability to paraphrase is an indication of understanding of what one has read. In paraphrasing, the author of the review connects the meanings of these sources to the proposed study, being careful to present the information correctly. The author of the review may wish to record quotations with quotation marks (including page numbers) for possible use in the written review. This is essential for avoiding accidental plagiarism. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. In which methods does substantive review of the literature take place after data analysis?

(Select all that apply.) a. Grounded theory b. Narrative inquiry c. Phenomenology d. Ethnography e. Quantitative descriptive ANS: A, C

In qualitative research, the purpose and timing of the literature review vary based on the type of study to be conducted. In general, phenomenologists believe that no further literature review should be undertaken until after the data have been collected and analyzed, so that the knowledge of the results of prior studies in the area do not intrude upon the researcher’s interpretation of the text of interviews and other data. Classical grounded theory researchers begin with “tabula rasa,” a blank slate, an attempt to know as little as possible about the area of study before they begin the research, so the only point of the perusal of the brief literature overview performed prior to enactment of the study is to discover whether this particular study has been performed before. As the process progresses, the researchers collect and analyze all data before they return to the literature, so that the entirety of the analysis is grounded in their data, not in the literature. When the core concept or process has been identified and data analysis is complete, the researcher theoretically samples the literature for extant theories that may assist in explaining and extending the emerging theory. The role of the literature review for ethnographic research is similar to role of the literature review for quantitative research. The ethnographic researcher is expected to prepare extensively before data collection, in order to familiarize oneself with the culture, and this includes detailed review of the literature. The literature review provides a background for conducting the study and interpreting the findings. DIF: Cognitive Level: Synthesis 2. Why would a reputable researcher use a secondary source instead of a primary one? (Select all

that apply.) a. The primary publication is written in a language not currently spoken. b. The primary source is located in a museum 1100 miles away, and the cost of travel to review it would be prohibitive. c. The primary publication is so steeped in jargon that it is very difficult to decipher. d. The researcher has limited time and cannot squander it searching for primary sources. e. The primary publication describes only the beginnings of a theory, and a later publication presents it in its entirety. f. There have never been any primary sources in this area. g. The primary publication is no longer in print, and there are no existent copies. ANS: A, B, C, E, G

Reasons to use a secondary source include: (1) The primary source has been destroyed or cannot be accessed; (2) the primary source is located at such a distance that the cost of travel to review it would be prohibitive; (3) the primary source is written in a language not currently spoken, or in one that the researcher has not mastered; (4) the primary publication is written in unfamiliar jargon that it is very difficult to decipher, but a secondary source analyzes and simplifies the material; and (5) the secondary source contains creative ideas or a unique organization of information not found in a primary source. DIF: Cognitive Level: Comprehension 3. What are the purposes of the literature review in quantitative research concerning patient

compliance with alternating leg pressure stockings (ALPs)? (Select all that apply.) a. It gives the researcher an overview of anecdotal reports about how it feels to the patient to wear ALPs. b. It allows the researcher to use the data from previous research on ALPs to add to

his or her database. c. It allows the researcher to construct theory about compliance with ALPs. d. It gives the researcher something with which to compare his or her findings on compliance with ALPs. e. It allows the researcher to discover previous research in the area of ALPs, so as to identify what is not known (the research gap). ANS: D, E

Quantitative research studies are shaped by the review of literature, whether descriptive, correlational, quasi-experimental, or experimental in design. Based on review of the literature, the researcher decides a quantitative study is the best way to address a particular research problem. The researcher makes preparations to design a study to add knowledge in the area of the identified gap. After data collection is complete, the researcher will analyze the data and then again use the literature to compare research findings to those of earlier studies, as well as to other related studies. The researcher’s goal is to integrate knowledge from the literature with new information obtained from the study in progress. DIF: Cognitive Level: Application 4. What might a researcher include in a preliminary review of the literature concerning

acupuncture and conscious sedation for major surgical procedures? (Select all that apply.) a. A research article from the Journal of Acupuncture comparing the use of acupuncture with general anesthesia b. Bryson’s Human Physiology textbook c. A research synthesis on alternatives to general anesthesia compiled by the Agency for Healthcare Research and Quality d. An article in the National Enquirer on the dangers of major surgery e. A master’s thesis on the use of acupuncture during closed reduction of radial-ulnar fractures f. A Wikipedia article on how acupuncture works g. A monograph written by a physician in a third world country who used acupuncture to control pain during surgical procedures ANS: A, B, C, E, F, G

“The literature” consists of all written sources relevant to the selected topic. It consists of printed and electronic newspapers, encyclopedias, conference papers, scientific journals, textbooks, other books, theses, dissertations, and clinical journals. Websites and reports developed by government agencies and professional organizations are also included. There is debate as to whether Wikipedia is an appropriate source for course assignments and scholarly papers. Wikipedia is helpful for gathering preliminary information on a topic. The preliminary information can be used to identify keywords and authors in a subsequent search for professional sources. Wikipedia is not peer-reviewed, and most teachers do not accept Wikipedia references as support for information for a formal paper. Scholarly papers and graduate course assignments may require exclusively peer-reviewed professional literature as source material. DIF: Cognitive Level: Analysis 5. It is appropriate to conduct a review of the literature in which circumstances? (Select all that

apply.) a. An ethnographic study is planned.

b. c. d. e.

A nurse is interested in conducting research on patients who “sundown.” One requirement for a graduate course paper is a written literature review. A hospital is attempting to develop a policy on bathing frequency for elders. The hospital attorney is preparing a brief, relative to a fall suffered by a patient.

ANS: A, B, C, D

Reviews of the literature for a course assignment vary depending on the level of educational program, the purpose of the assignment, and the expectations of the instructor. The depth, scope, and breadth of a literature review increase as students move from undergraduate courses to master’s level courses to doctoral courses. Another reason to review the literature is to determine whether clinical practice is consistent with the latest research evidence. In this context, it is necessary to identify all studies that provide evidence of a particular nursing intervention, critically appraise the strength of each individual study’s research processes, synthesize the findings of all the studies, and provide an analytic summary. The role of the literature review for ethnographic research is similar to role of the literature review for quantitative research. The ethnographic researcher is expected to prepare extensively before data collection, in order to familiarize oneself with the culture, and this includes detailed review of the literature. The literature review provides a background for conducting the study and interpreting the findings. Quantitative research studies are shaped by the review of literature, whether descriptive, correlational, quasi-experimental, or experimental in design. Based on review of the literature, the researcher decides a quantitative study is the best way to address a particular research problem. The researcher makes preparations to design a study to add knowledge in the area of the identified gap. DIF: Cognitive Level: Analysis 6. The review of literature in quantitative research directs everything from the first ideas about

the study variables through recommendations based upon the study’s conclusions. What are outputs of the literature review in quantitative research? (Select all that apply.) a. Development of conceptual definitions of concepts b. Determining the statistical power of the sample c. Determination of how many subjects will drop out of the study d. Description of what studies have been performed, so as to provide initial direction for the study method e. Interpretation of the study findings, in comparison with previous research ANS: A, D, E

Table 7-1 describes the role of the literature throughout the development and implementation of a quantitative study. The types of sources needed and the way the researcher searches the literature vary throughout the study. The introduction section uses relevant sources to summarize the background and significance of the research problem. The review of the literature section includes both theoretical and empirical sources that document current knowledge of the problem. The researcher develops the framework section from theoretical literature. If little theoretical literature is found, the researcher may choose to develop a tentative theory to guide the study based on findings of previous research studies (see Chapter 8 for more information), and on the posited relationships in the current study’s research hypothesis. In the methods section, the design, sample, measurement methods, treatment, and data collection processes of the planned study are described. Research texts, describing standards of methodological rigor, and previous studies are cited in this section. In the results section, the researcher cites sources for the different types of statistical analyses conducted and the computer software used to conduct these analyses. The discussion section of the research report begins with what the results mean, in light of the results of previous studies. Conclusions are drawn that are a synthesis of the findings from previous studies and from the current study. DIF: Cognitive Level: Analysis 7. In phenomenology, often the review of the literature is conducted after data analysis is

complete. What is the reason for this? (Select all that apply.) a. The data analysis phase of phenomenology includes a literature review. b. Phenomenology is data-free, and analyses are based only on the interpretation of the researcher. c. Some phenomenologists do believe that one can “bracket” what is known, in order to perform an unbiased analysis, but it seems pointless to absorb information just to then put it aside, so literature review is usually postponed. d. Some phenomenologists don’t believe that one can “bracket” what is known, in order to perform an unbiased analysis of the data, so they try to minimize what they read about the topic of the study until data analysis is complete. e. The review of the literature provides an objective cross-check for the researcher’s interpretation. ANS: C, D

Evidence to the contrary was provided in several studies of efficacy but never examined in a context of “the adolescent at sea with the ghost of his losses” (Reynolds, 2011). The student’s reference list contains the following citation for this work: Reynold, A. R. (2010). Never underestimate depression. Journal of Applied Psychology. What is wrong with it? (Select all that apply.) a. The reference list should restate the quotation.

b. c. d. e.

The reference is incomplete, lacking volume number and page numbers. The years of the citation differ. The author’s name is spelled differently in the citation and in the reference list. No page number is provided for the direct quotation.

ANS: B, C, D, E

Sources that will be cited in a paper or recorded in a reference list should be cross-checked two or three times to prevent errors. Questions that will identify common errors are displayed in Box 7-3. To prevent these errors, the author checks all the citations within the text of the literature review and each citation in the reference list. DIF: Cognitive Level: Application

Chapter 08: Frameworks Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. What is a framework? a. The abstract, logical structure of meaning b. A concept at a high level of abstraction with a very general meaning c. An integrated set of defined concepts, existence statements, and relational

statements that can be used to describe, explain, predict, or control that phenomenon d. A diagram that expresses the interrelationships of concepts and statements ANS: A

A theoretical framework is an abstract, logical structure of meaning that guides the development of a study and enables the researcher to link the findings to the body of knowledge in nursing. A concept is a term that abstractly describes and names an object, a phenomenon, or an idea, thus providing it with a distinct identity or meaning. Concepts can vary in their levels of abstraction. At high levels of abstraction, concepts that naturally cluster together are called constructs. A theory consists of a set of defined concepts and relational statements that provide a structured way to think about a phenomenon. Diagrams of research frameworks are conceptual maps. A conceptual map summarizes and integrates visually the theoretical structure of a study. DIF: Cognitive Level: Identification 2. What is a concept? a. The abstract, logical structure of meaning b. A term that abstractly describes and names an object, a phenomenon, or an idea,

thus providing it with a distinct identity or meaning c. An integrated set of defined concepts, existence statements, and relational

statements that can be used to describe, explain, predict, or control that phenomenon d. A diagram that expresses the interrelationships of concepts and statements ANS: B

A theoretical framework is an abstract, logical structure of meaning that guides the development of a study and enables the researcher to link the findings to the body of knowledge in nursing. A concept is a term that abstractly describes and names an object, a phenomenon, or an idea, thus providing it with a distinct identity or meaning. A theory consists of an integrated set of defined concepts and relational statements that provide a structured way to think about a phenomenon. Diagrams of research frameworks are conceptual maps. A conceptual map summarizes and integrates visually the theoretical structure of a study. DIF: Cognitive Level: Identification 3. What is a construct? a. The abstract, logical structure of meaning b. A concept at a high level of abstraction with a very general meaning

c. An integrated set of defined concepts, existence statements, and relational

statements that can be used to describe, explain, predict, or control that phenomenon d. A term that abstractly describes and names an object, a phenomenon, or an idea, thus providing it with a distinct identity or meaning ANS: B

A theoretical framework is an abstract, logical structure of meaning that guides the development of a study and enables the researcher to link the findings to the body of knowledge in nursing. A concept is a term that abstractly describes and names an object, a phenomenon, or an idea, thus providing it with a distinct identity or meaning. Concepts can vary in their levels of abstraction. At high levels of abstraction, concepts that naturally cluster together are called constructs. A theory consists of an integrated set of defined concepts and relational statements that provide a way to think about a phenomenon. Diagrams of research frameworks are conceptual maps. A conceptual map summarizes and integrates visually the theoretical structure of a study. DIF: Cognitive Level: Identification 4. What is concept analysis? a. Evaluation of the interrelationships of the concepts and statements in a framework b. The process of describing and naming a previously unrecognized concept c. Modifying conceptual definitions from other disciplines to be consistent with

nursing usage d. A strategy through which a set of characteristics essential to the connotative

meaning of a concept is identified ANS: D

Concept analysis is a strategy that identifies a set of characteristics essential to defining the connotative meaning of a concept. The process of describing and naming a previously unrecognized concept is concept synthesis. In concept derivation, a concept is transposed from one of field of knowledge to another. DIF: Cognitive Level: Identification 5. What is concept synthesis? a. A diagram of the interrelationships between concepts and statements in a

framework b. The process of describing and naming a previously unrecognized concept c. Modifying conceptual definitions from other disciplines to be consistent with

nursing usage d. A strategy through which a set of characteristics essential to the connotative

meaning of a concept is identified ANS: B

6. What is concept derivation? a. The process of distilling meaning from concepts and statements in a framework b. The process of describing and naming a previously unrecognized concept c. Modifying conceptual definitions from other disciplines to be consistent with

nursing usage d. A strategy through which a set of characteristics essential to the connotative

meaning of a concept is identified ANS: C

Concept analysis is a strategy that identifies a set of characteristics essential to defining the connotative meaning of a concept. The process of describing and naming a previously unrecognized concept is concept synthesis. In concept derivation, a concept is transposed from one of field of knowledge to another. DIF: Cognitive Level: Identification 7. What is a conceptual model? a. A model made up of constructs, between which a relationship may or may not

exist b. A set of highly abstract, related constructs c. An integrated set of defined concepts, existence statements, and relational

statements that can be used to describe, explain, predict, or control that phenomenon d. A diagram that expresses the interrelationships of concepts and statements ANS: B

A conceptual model, one type of which is known as a grand theory, is a set of highly abstract, related constructs. A conceptual model broadly explains phenomena of interest, expresses assumptions, and reflects a philosophical stance. A theory consists of an integrated set of defined concepts and relational statements that provide a way to think about a phenomenon. Diagrams of research frameworks are conceptual maps. A conceptual map summarizes and integrates visually the theoretical structure of a study. DIF: Cognitive Level: Identification 8. What is a conceptual map? a. A model connecting objects, phenomena, or ideas b. A set of highly abstract, related constructs c. An integrated set of defined concepts, existence statements, and relational

statements that can be used to describe, explain, predict, or control that phenomenon d. A diagram that expresses the interrelationships of concepts and statements in a framework ANS: D

A theoretical framework is an abstract, logical structure of meaning that guides the development of a study and enables the researcher to link the findings to the body of knowledge in nursing. A concept is a term that abstractly describes and names an object, a phenomenon, or an idea, thus providing it with a distinct identity or meaning. Concepts can vary in their levels of abstraction. At high levels of abstraction, concepts that naturally cluster together are called constructs. A theory consists of an integrated set of defined concepts and relational statements that provide a way to think about a phenomenon. Diagrams of research frameworks are conceptual maps. A conceptual map summarizes and integrates visually the theoretical structure of a study. A conceptual model broadly explains phenomena of interest, expresses assumptions, and reflects a philosophical stance. DIF: Cognitive Level: Identification 9. What is a theory? a. The abstract, logical structure of meaning b. A concept at a high level of abstraction with a very general meaning c. An integrated set of defined concepts, existence statements, and relational

statements that can be used to describe, explain, predict, or control that phenomenon d. A diagram that expresses the interrelationships of concepts and statements ANS: C

A theoretical framework is an abstract, logical structure of meaning that guides the development of a study and enables the researcher to link the findings to the body of knowledge in nursing. A concept is a term that abstractly describes and names an object, a phenomenon, or an idea, thus providing it with a distinct identity or meaning. Concepts can vary in their levels of abstraction. At high levels of abstraction, concepts that naturally cluster together are called constructs. A theory consists of an integrated set of defined concepts and relational statements that provide a way to think about a phenomenon. A conceptual map summarizes and integrates visually the theoretical structure of a study. DIF: Cognitive Level: Identification 10. An author makes a hypothetical relational statement, linking seven concepts to a central idea,

and denoting which ones are causes and which are results. What is this hypothetical relational statement called? a. A theoretical map b. A point of view c. A hybrid correlational array d. A framework ANS: D

A theoretical framework is an abstract, logical structure of meaning that guides the development of a study and enables the researcher and reader to link the findings to the body of knowledge in nursing. A relational statement is the explanation of the connection between or among concepts. Relational statements provide the structure of a framework. DIF: Cognitive Level: Application

11. A nursing professor is interested in factors related to nursing student satisfaction with the

pre-licensure nursing program. The professor finds a relationship of r = −0.72 (p <0.05) between weekly hours of employment and nursing program satisfaction. How should the professor interpret these findings? a. There is a strong, positive relationship between weekly hours of employment and nursing program satisfaction. b. There is a strong, negative relationship between weekly hours of employment and nursing program satisfaction. c. There is a weak, negative relationship between weekly hours of employment and nursing program satisfaction. d. There is no relationship between weekly hours of employment and nursing program satisfaction. ANS: B

A relational statement is the explanation of the connection between concepts. Relational statements describe the direction, shape, strength, sequencing, probability of occurrence, necessity, and sufficiency of a relationship. One statement may have several of these characteristics; each is not exclusive of the others. The strength of a relationship is the amount of variation explained by the relationship. If two concepts are related, some of the variation in one concept may be found to be associated with variation in another concept. The statistic r is the result obtained by performing the statistical procedure known as Pearson’s product-moment correlation. A value of 0 indicates no relationship, whereas a value of +1 or −1 indicates a perfect relationship. The closer to +1 or −1 the correlation is, the stronger the relationship between the variables. A calculated value of −0.72 denotes a strong, negative relationship. DIF: Cognitive Level: Application 12. What is the difference between a concurrent relationship and a sequential one, in terms of A

and B? a. In a sequential relationship, A occurs before B; in a concurrent relationship, A occurs independently of B. b. In a concurrent relationship, causation is clear; in a sequential relationship, causation is unclear. c. Variable values do not change at the exact same time in a sequential relationship, whereas they change at the exact same time in a concurrent one. d. Measurement of variables is possible in a sequential relationship, whereas measurement of variables is impossible in a concurrent relationship. ANS: C

A relational statement is the explanation of the connection between concepts. Relational statements describe the direction, shape, strength, sequencing, probability of occurrence, necessity, and sufficiency of a relationship. The amount of time that elapses between one concept and another is stated as the sequential nature of a relationship. If the two concepts occur simultaneously or are measured at the same time, the relationship is concurrent. When there is a change in one concept, there is change in the other at the same time. If one concept changes and the second concept changes later, the relationship is sequential. DIF: Cognitive Level: Evaluation

13. A variable is more concrete than a concept. A concept is more concrete than a construct.

Which one is the most abstract? a. Construct b. Concept c. Variable d. Measurement values ANS: A

A concept is a term that abstractly describes and names an object, a phenomenon, or an idea, thus providing it with a distinct identify or meaning. Concepts can vary in their levels of abstraction. At high levels of abstraction, concepts that naturally cluster together are called constructs. Concepts are often described as the building blocks of theory: useful, in an amorphous sort of way, but difficult to tack down because of their abstractness. To make a concept concrete, the researcher must identify how it can be measured. A concept made measureable is referred to as a variable. The word “variable” implies that the values associated with the term can vary from one instance to another. DIF: Cognitive Level: Synthesis 14. A nurse researcher has a notion that neonates perceive all interactions with humans as either

stressors or comfort. The researcher is conducting qualitative research to describe the types of stressors or comfort that neonates typically experience in the first 24 hours of life. What is the best way to describe the researcher’s notion? a. A framework b. A middle-range theory c. An idea d. A hypothesis ANS: C

A theoretical framework is an abstract, logical structure of meaning that guides the development of a study and enables the researcher to link the findings to the body of knowledge in nursing. Middle-range theories present a partial view of nursing reality. These theories are less abstract and address more specific phenomena than grand theories do. They directly apply to practice, with a focus on explanation of the specifics of condition, symptom, diagnosis, or process, and on implementation. Hypotheses, which are a form of statement consisting of an expressed relationship between variables, are at the concrete level, representing a low level of abstraction. At this stage, the researcher has an idea about a phenomenon and will use qualitative study to explore the idea further, possibly identifying specific variables for future study. DIF: Cognitive Level: Application 15. The Process of Incorporation of a Rescue Dog into One’s Home

Wariness  Mutual Protectiveness  Compassion → Adoption What is this? a. A relational statement b. A research framework c. A theory d. A conceptual map ANS: D

A theoretical framework is an abstract, logical structure of meaning that guides the development of the study and enables the researcher to link the findings to the body of knowledge in nursing. A relational statement is the explanation of the connection between or among concepts. A conceptual map summarizes and integrates visually the theoretical structure of a study. A theory consists of a set of defined concepts and relational statements that provide a structured way to think about a phenomenon. DIF: Cognitive Level: Comprehension 16.

High to low Highest level of abstraction Middle level of abstraction Lowest level of abstraction Specific way variables will be measured

Level Construct (general statement) Conceptual (theory) Variable (hypothesis) Operationalizations

“Happiness is a requisite of the human condition” is a statement written at which level of abstraction? a. Construct level (general construct) b. Conceptual level (specific theoretical statement) c. Hypothesis level (composed of the study variables) d. Measurement level (consisting of the measurement values) ANS: A

High to low Highest level of abstraction Middle level of abstraction Lowest level of abstraction Specific way variables will be measured

Level Construct (general statement) Conceptual (theory) Variable (hypothesis) Operationalizations

“Chronic disappointment in goal achievement produces an attenuated period of decreased goal-setting” is a statement written at which level of abstraction? a. Construct level (general construct) b. Conceptual level (specific theoretical statement) c. Hypothesis level (composed of the study variables) d. Measurement level (consisting of the measurement values) ANS: B

High to low Highest level of abstraction Middle level of abstraction Lowest level of abstraction Specific way variables will be measured

Level Construct (general statement) Conceptual (theory) Variable (hypothesis) Operationalizations

“If you give a raccoon a cookie, he will become a permanent resident on your property” is a statement written at which level of abstraction? a. Construct level (general construct) b. Conceptual level (specific theoretical statement) c. Hypothesis level (composed of the study variables) d. Measurement level (consisting of the measurement values) ANS: C

High to low Highest level of abstraction Middle level of abstraction Lowest level of abstraction Specific way variables will be measured

Level Construct (general statement) Conceptual (theory) Variable (hypothesis) Operationalizations

“Intelligence is measured as the subject’s score on the Stanford Binet Intelligence Quotient Test” and “Ability to juggle is operationally defined as the number of seconds, as timed with the research assistant’s stopwatch, that the subject can keep three oranges in the air simultaneously” are statements written at which level of abstraction? a. Construct level (general construct) b. Conceptual level (specific theoretical statement) c. Hypothesis level (composed of the study variables) d. Measurement level (consisting of the measurement values) ANS: D

Statements about the same two conceptual ideas can be made at various levels of abstractness. The relational statements found in conceptual models and grand theories (general propositions) are at a highest level of abstraction. Relational statements found in the middle-range theories (specific propositions) are at a moderate level of abstraction. Hypotheses, which are a form of statement consisting of an expressed relationship between variables, are at the concrete level, representing a low level of abstraction. DIF: Cognitive Level: Analysis 20. Which statement demonstrates a sequential relationship? a. As “A” changes in value, “B” does not. b. As “A” changes, “B” may or may not change. c. After “A” changes, “B” changes. d. When “A” changes, “B” changes at the same time. ANS: C

The amount of time that elapses between one concept and another is stated as the sequential nature of a relationship. If the two concepts occur simultaneously or are measured at the same time, the relationship is concurrent. When there is a change in one concept, there is change in the other at the same time. If a change in one concept now influences changes in second concept at a later time, the relationship is sequential. DIF: Cognitive Level: Analysis 21. Infants and children receive immunizations so that they do not become ill with various

diseases. What type of relationship exists between receiving an immunization and the state of immunity? a. Necessary b. Sufficient c. Contingent d. Negative linear ANS: B

In a necessary relationship, one concept must occur for the second concept to occur. A sufficient relationship states that when the first concept occurs, the second concept will occur, regardless of the presence or absence of other factors. A contingent relationship will occur only if a third concept is present. A negative linear relationship implies that as a concept changes, the other concept in the statement changes in the opposite direction. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. What statements demonstrate a positive linear relationship? (Select all that apply.) a. As “A” increases in value, so does “B.” b. As “A” changes in value, “B” may or may not change. c. As “A” decreases in value, so does “B.” d. As “A” increases in value, “B” decreases in value. e. If “A” occurs, then “B” occurs, but only if “C” occurs. ANS: A, C

The direction of a relationship may be positive, negative, or unknown. A positive linear relationship implies that as one concept changes (the value or amount of the concept increases or decreases), the second concept will also change in the same direction. DIF: Cognitive Level: Analysis 2. What is the purpose of a framework, in a study of hypoxia as a possible cause for autism in

the genetically susceptible? (Select all that apply.) a. It ensures that the researcher treats the subjects with autism ethically during the study. b. It implies that the study is well constructed and logical, and that the researcher’s reasoning about causes of autism is correct. c. The framework’s relationships between autism and other concepts assist the researcher to formulate research questions and hypotheses. d. It demonstrates for the reader where the findings of this study related to hypoxia fit into all that is known about autism. e. It gives the reader a collection of connected ideas, from which to think about both the study and the entire research area of autism’s causes. ANS: C, D, E

A theoretical framework is an abstract, logical structure of meaning that guides the development of a study and enables the researcher to link the findings to the body of knowledge in nursing. Clear relational statements are essential for constructing an integrated framework that guides the development of a study’s objectives, questions, and hypotheses. The types of relationships described determine the study design and indicate the types of statistical analyses that may be used to answer the research question. DIF: Cognitive Level: Application 3. A framework about bipolar disorder contains information about the direction, sequencing, and

strength of the relationship between treatment of the bipolar disorder and client functioning, over time, because it is a relational statement. What other components may be included, so that the relational statement is meaningful to research? (Select all that apply.) a. Shape b. Exclusivity c. Exhaustiveness d. Sufficiency e. Symmetry ANS: A, D, E

A relational statement is the explanation of the connection between or among concepts. Relational statements describe the direction, shape, strength, sequencing, probability of occurrence, necessity, and sufficiency of a relationship. One statement may have several of these characteristics; each characteristic is not exclusive of the others. The strength of a relationship is the amount of variation explained by the relationship. DIF: Cognitive Level: Application 4. Which of the following are variables? (Select all that apply.) a. Sanctity b. How many times the experimental monkey rings the bell

c. Déja vu d. The number of speeding tickets Richard receives in July of this year e. Darwin’s theory of evolution ANS: B, D

To make a concept concrete, the researcher must identify how it can be measured. A concept made measurable is referred to as a variable. A variable is more specific than a concept and implies that the term is clearly defined and measurable. The word “variable” implies that the values associated with the term can vary from one instance to another. The key concept here is measurement: can this idea be measured, as stated? DIF: Cognitive Level: Application 5. Which of the following are concepts but not variables? (Select all that apply.) a. Trepidation b. How many tries it takes to score a basketball free throw c. Loneliness d. Weight on a kilogram scale e. The Heisenberg uncertainty principle ANS: A, C

To make a concept concrete, the researcher must identify how it can be measured. A concept made measurable is referred to as a variable. A variable is more specific than a concept and implies that the term is clearly defined and measurable. The word “variable” implies that the values associated with the term can vary from one instance to another. The key concept here is measurement: can this idea be measured, as stated? DIF: Cognitive Level: Application 6. Directional statements are relational statements with the specific relationship between

variables defined. These are diagrammatically represented by letters and arrows. The diagram as a. b. c. d. e. f.

means which of the following? (Select all that apply.) B causes D only a small amount of the time. When D is high, B is low in value. When B is high, D is low in value. There is no relationship between B and D. B is smaller than D. D is smaller than B.

ANS: B, C

DIF: Cognitive Level: Synthesis 7. This figure provides an illustrated example of a linear relationship. What does it mean? (Select

all that apply.)

a. As the independent variable becomes larger, the dependent variable becomes b. c. d. e. f.

larger. There is an indirect link between “High” and the independent variable. As the dependent variable becomes smaller, the independent variable becomes smaller. The independent variable causes the dependent variable. The strength of the relationship is large because the portions of the concepts are explained. When the independent variable is absent, the dependent variable is also absent.

ANS: A, C

A relational statement is the explanation of the connection between or among concepts. Relational statements describe the direction, shape, strength, sequencing, probability of occurrence, necessity, and sufficiency of a relationship. The strength of a relationship is the amount of variation explained by the relationship. In a linear relationship, the relationship between two concepts remains consistent regardless of the values of each of the concepts. For example, if the value of Concept B increases by 1 point each time the value of Concept A increases by 2 points, then the values continue to increase proportionally whether the values are 2 and 4 or 200 and 400. We can diagram relationships between concepts using a vertical axis and a horizontal axis, with each axis representing the score on one of the concepts. Each subject’s paired scores on the two concepts are plotted as a dot on the diagram. If the relationship between the concepts is linear, most of the dots will be clustered around a straight line. In a curvilinear relationship, the relationship between two concepts varies according to the relative values of the concepts. A negative relationship implies that as a concept changes, the other concept in the statement changes in the opposite direction. DIF: Cognitive Level: Synthesis 8. This diagram refers to correlational relationships. What does it mean? (Select all that apply.)

a. b. c. d.

A negative relationship is smaller than no relationship. A negative relationship occurs before a positive relationship. Negative relationships evolve in a positive direction. The strength of the relationship depends upon its numerical value, not the positive or negative sign preceding that number.

e. There is no strength in a negative or positive relationship. f. A positive relationship is better than none; no relationship is better than a negative

one. g. The further away from zero, the stronger the relationship. ANS: D, G

curvilinear relationship signify? (Select all that apply.)

a. The relationship is more complex than can be illustrated by a straight line. b. The most positive value of one variable is seldom associated with the most positive

value or the most negative value of the other variable. c. The value of one variable cannot be predicted if the other is known. d. A relationship represented by an arc explains a large portion of the variation in the

independent variable. e. The relationship between the variables is statistically significant. f. An increase in the value of one variable may be associated with either an increase

or a decrease in the value of the other. ANS: A, B, F

10. How does the researcher know that a certain framework is the correct one for a planned

research study? (Select all that apply.) a. The framework has been tested, using quantitative research. b. The framework contains concepts that the researcher is studying. c. Relationships among concepts are similar to the ones the researcher is studying. d. Grounded theory research generated the framework. e. The framework helps explain the anticipated or expected research results. f. The type of research selected by the researcher (the method) agrees with the relationships in the framework. ANS: B, C, E, F

Chapter 09: Ethics in Research Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A research study offers elderly men, who have in the past been prison inmates, $1,500 for

participation in an all-day workshop at which they agree to be hypnotized and tell stories of incarceration, which later are published. The research participants are allowed to listen to the tapes of what the men said under hypnosis and to withdraw permission to use any part of the information. Why is this scenario a violation of self-determination? a. Allowing participants to withdraw permission to use part of the research information violates the study integrity and represents deception. b. It is an example of coercion. c. Prisoners are a vulnerable population and should not be used as research participants. d. What is said under hypnosis may not be true. ANS: B

The right to self-determination is based on the ethical principle of respect for persons. This principle holds that because humans are capable of self-determination, or controlling their own destiny, they should be treated as autonomous agents who have the freedom to conduct their lives as they choose without external controls. A participant’s right to self-determination can be violated through the use of (1) coercion, (2) covert data collection, and (3) deception. Coercion occurs when one person intentionally presents another with an overt threat of harm or the lure of excessive reward to obtain his or her compliance. In the example, offering elderly men $1500 for one day could be considered as offering an excessive reward; therefore, it is an act of coercion violating the human right to self-determination. DIF: Cognitive Level: Analysis 2. A researcher working for Google collects data on fair treatment in the workplace. She

attempts to attach one of the raw data forms to an e-mail message to herself, so that she can finish the data analysis at home that evening, but accidentally sends it to another employee who had provided data for the study. The two study participants, coincidentally, have an identical opinion about fair treatment in the workplace. This best describes an example of a violation of which human right? a. Confidentiality b. Fair treatment c. Protection from harm d. None of these—no ethical violation occurred because the two participants share a point of view. ANS: A

Confidentiality is the researcher’s management of private information shared by a participant that must not be shared with others without the authorization of the participant. In the example, sending one research participant the raw data of a different participant is a direct breach of confidentiality. A breach in confidentiality can occur when a researcher, by accident or direct action, allows an unauthorized person to gain access to raw study data. The right to fair treatment is based on the ethical principle of justice. This principle holds that each person should be treated fairly and should receive what he or she is due or owed. The right to protection from discomfort and harm is based on the ethical principle of beneficence, which holds that one should do good and, “above all, do no harm.” DIF: Cognitive Level: Application 3. In a study of outpatients experiencing panic attacks, a researcher was working in a busy clinic

waiting room and left his computer unattended while consenting a new study participant. A transcription of a patient interview was displayed, and at the end of the transcription were the patient’s medical record number and a list of medications currently taken. The researcher had not closed down the screen and when he returned to the room, he found an adult patient playing a video game on the computer. This best describes an example of a violation of which human right? a. Protection from the harm of exposure b. Security c. Confidentiality d. Privacy ANS: D

Privacy is an individual’s right to determine the time, extent, and general circumstances under which personal information will be shared with or withheld from others. This information consists of one’s attitudes, beliefs, behaviors, opinions, and records. The Privacy Act of 1974 provided the initial protection of an individual’s privacy. Because of this act, data collection methods were to be scrutinized to protect participants’ privacy, and data cannot be gathered from participants without their knowledge. Individuals also have the right to access their records and to prevent access by others. The intent of this act was to prevent the invasion of privacy that occurs when private information is shared without an individual’s knowledge or against his or her will. Invading an individual’s privacy might cause loss of dignity, friendships, or employment or create feelings of anxiety, guilt, embarrassment, or shame. The HIPAA Privacy Rule expanded the protection of an individual’s privacy, specifically his or her protected individually identifiable health information and described the ways in which covered entities can use or disclose this information. De-identifying health data involves removing 18 elements that could be used to identify an individual. An important one on this list is the individual’s medical record number. In the example, the researcher’s use of an actual patient identification number on a transcription risks the human right to privacy; a code number should have been used instead. DIF: Cognitive Level: Application 4. A patient in a research study will receive either the customary medication to treat the patient’s

metastatic colon cancer or a new medication that has shown better results in animal studies and in one small study with humans. This is what kind of research? a. Coercive research b. Correlational research

c. Therapeutic research d. Dangerous research ANS: C

Therapeutic research gives the patient an opportunity to receive an experimental treatment that might have beneficial results. In therapeutic nursing research, the individual participant has the potential to benefit from the procedures, such as skin care, range of motion, touch, and other nursing interventions, that are implemented in the study. The benefits might include improvement in the participant’s physical condition, which could facilitate emotional social benefits. The participant also may benefit from the additional attention of and interaction with a healthcare professional. In addition, knowledge generated from the research might expand the participants’ and their families’ understanding of health. Nontherapeutic research is conducted to generate knowledge for a discipline, and the results from the study might benefit future patients but will probably not benefit those acting as research participants. The Declaration of Helsinki differentiated therapeutic research from nontherapeutic research. Neither descriptive nor correlational research involves treatment or manipulation of a variable. There is no evidence of coercion. DIF: Cognitive Level: Application 5. A graduate student receives a mailed survey packet asking the student to participate in

research about unpleasant experiences in graduate school. The student is asked to return the survey, with the statement, “Return of this instrument implies consent.” Why does this constitute consent? a. Studies like this are exempt from institutional review board oversight, so consent is not required. b. Not returning the survey constitutes refusal, and participants may indeed refuse by not completing the survey. The opposite is equally true. c. The study is anonymous, so there is no risk of disclosure. d. Only interventional research requires consent. ANS: B

The requirements for written consent may be waived in minimal risk research. For example, if questionnaires are used to collect low-risk data, a signed consent form from the participants might not be necessary. The participant’s completion of the questionnaire may serve as consent. The top of the questionnaire might contain a statement such as “Your completion of this questionnaire indicates your consent to participate in this study.” DIF: Cognitive Level: Analysis 6. Both the participant in the experimental group who receives an experimental treatment and the

participant in the control group who receives the control treatment are considered to be participants in therapeutic research. Why is this? a. A patient in an experimental research study who elects to be a member of the experimental group knows he or she will be receiving the experimental treatment. b. Each patient who is consented to be a research participant in an experimental study, in which the treatment has potentially beneficial results, has the potential to receive a therapeutic intervention. c. The research is designed to measure the effect of the therapeutic treatment, as compared with the usual therapeutic treatment; hence, this is therapeutic research. d. Each participant is blind to treatment.

ANS: C

Therapeutic research gives the patient an opportunity to receive an experimental treatment that might have beneficial results. In experimental research, being a participant in a therapeutic study means only that the participant is recruited into the study and randomly assigned to either treatment or control group, not that the participant receives the experimental treatment. In experimental research, participants must be randomly assigned to either the intervention group or the control group; they are not allowed to elect to be a member of a certain group. DIF: Cognitive Level: Evaluation 7. In what way could the researchers in the Willowbrook study have designed their research on

the hepatitis virus so that it was ethically acceptable? a. The researchers could have given each participant a chance to assent. b. The researchers could have performed their study on persons who were capable of full assent. c. The researchers could have made the study available at many institutions for the mentally retarded. d. The researchers could have performed descriptive research on persons already infected with hepatitis. ANS: D

From the mid-1950s to the early 1970s, Dr. Saul Krugman at Willowbrook State School, a large institution for cognitively impaired persons in Brooklyn, New York, conducted research on hepatitis A. The participants, all children, were deliberately infected with the hepatitis A virus. During the 20-year study, Willowbrook closed its doors to new inmates because of overcrowded conditions. However, the research ward continued to admit new inmates. To gain a child’s admission to the institution, parents were forced to give permission for the child to be a study participant. Hepatitis A affects the liver, producing vomiting, nausea, and tiredness, accompanied by jaundice. Because, the principle of beneficence requires the researcher to do good and “above all, do no harm,” the only way to study a virus that clearly harms people is noninterventionally: through descriptive or correlational research. DIF: Cognitive Level: Synthesis 8. The right an individual has to be told that he is a potential participant in a research study and

may decide not to be so best defines which human right? a. Beneficence b. Justice c. Privacy d. Self-determination ANS: D

The right to self-determination holds that because humans are capable of self-determination, or making their own decisions, they should be treated as autonomous agents who have the freedom to conduct their lives as they choose without external controls. Privacy is an individual’s right to determine the time, extent, and general circumstances under which personal information will be shared with or withheld from others. Justice holds that each person should be treated fairly and should receive what he or she is due or owed. The right to protection from discomfort and harm is based on the ethical principle of beneficence, which holds that one should do good and “above all, do no harm.”

DIF: Cognitive Level: Application 9. The right an individual has to receive treatment even if that individual decides not to

participate in the research best defines which human right? a. Beneficence b. Justice c. Privacy d. Respect ANS: B

The right to fair treatment is based on the ethical principle of justice. Privacy is the right an individual has to determine the time, extent, and general circumstances under which personal information will be shared or withheld from others. Such information consists of one’s attitudes, beliefs, behaviors, opinions, and records. The right to protection from discomfort and harm is based on the ethical principle of beneficence, which holds that one should do good and “above all, do no harm.” The right to self-determination is based on the ethical principle of respect for persons. DIF: Cognitive Level: Application 10. To take positive action to prevent any harm to the research participants best defines which

ethical principle? a. Beneficence b. Justice c. Privacy d. Respect ANS: A

The right to protection from discomfort and harm is based on the ethical principle of beneficence, which holds that one should do good and, “above all, do no harm.” This includes positive actions taken to prevent harm to research participants. Privacy is the right an individual has to determine the time, extent, and general circumstances under which personal information will be shared or withheld from others. Such information consists of one’s attitudes, beliefs, behaviors, opinions, and records. The right to fair treatment is based on the ethical principle of justice. The right to self-determination is based on the ethical principle of respect for persons. DIF: Cognitive Level: Comprehension 11. An Institutional Review Board (IRB) assures that (1) the rights and welfare of the individuals

involved are protected, (2) appropriate methods are used to secure informed consent, and (3) potential benefits of the investigation are greater than the risks. Which is an example of how the IRB determines the level of potential risk? a. It requires the researcher to provide a list of potential benefits to the clients and the results of a pilot study verifying this. b. It compels the researcher to disclose the researcher’s consenting process. c. It provides for a supervisor from IRB to be present for all data collection. d. It reviews the researcher’s description of the study’s potential risks and compares them with everyday risk.

ANS: D

The functions and operations of an IRB involve the review of research at three different levels: (1) exempt from review, (2) expedited review, and (3) complete review. The IRB chairperson and/or committee, not the researcher, decides the level of the review. Studies usually are exempt from review if they pose no apparent risks for research participants. Studies that have risks that are viewed as minimal are expedited in the review process. DIF: Cognitive Level: Synthesis 12. A researcher who is also a university professor is performing a multi-site study, in which

on-site interviews are conducted with nurses in five hospitals in a major city. Each hospital has an Institutional Review Board (IRB). From how many institutional review boards or committees must the researcher obtain permission to conduct the study? a. Six—each of the five hospitals, and the university b. One—only the university c. Five—only the hospitals d. None—educational research is exempt from review ANS: A

Universities, hospital corporations, and many managed care centers maintain IRBs to promote the conduct of ethical research and protect the rights of prospective participants at these institutions, as required since 1974. If both a university and a hospital, or if more than one hospital, should be involved in a research study, both IRBs must give permission for the study to be conducted. This poses significant expenditure of time for such research. DIF: Cognitive Level: Application 13. What specific area of ethics does the Health Insurance Portability and Accountability Act

(HIPAA) address? a. Privacy b. Justice c. Coercion to participate in a research study d. Informed consent ANS: A

The privacy and confidentiality of health information became a greater concern for patients and the public with the advent of electronic transfer of data. The HIPAA Privacy Rule established the category of protected health information (PHI). The rule allows covered entities, such as health plans, healthcare clearinghouses, and healthcare providers, to use or disclose PHI to others only in certain situations. DIF: Cognitive Level: Comprehension 14. A researcher is applying for renewal of a large federal grant, without which his very

promising research on panic disorder cannot continue. He is completing renewal forms, which include a synopsis of his results, to date. If he excludes two of the participants with very severe panic disorder and three with mental health disorders of another kind, the results are statistically significant. He writes the report and does not mention the five participants he excluded. What word best describes this researcher’s actions? a. Beneficence b. Fabrication

c. Falsification d. Plagiarism ANS: C

Falsification of research is manipulating research materials, equipment, or processes, or changing or omitting data or results, such that the research is not accurately represented in the research record. Fabrication in research is the making up of results and the recording or reporting of them. Plagiarism is the appropriation of another person’s ideas, processes, results, or words without giving appropriate credit, including those obtained through confidential review of others’ research proposals and manuscripts. The principle of beneficence requires the researcher to do good and “above all, do no harm.” DIF: Cognitive Level: Application 15. A researcher is applying for a grant renewal, on the topic of a promising new treatment for

liver cancer. The researcher’s group has used the treatment for 13 participants. The results, 9 responded and 4 did not, are not statistically significant. However, if the researcher entered each patient as three different people and reported the results as 27 responded and 12 did not, the results would be statistically significant. If the researcher chose to do this, what would it represent? a. Beneficence b. Fabrication c. Falsification d. Plagiarism ANS: B

Fabrication in research is the making up of results and the recording or reporting of them. Falsification of research is manipulating research materials, equipment, or processes, or changing or omitting data or results such that the research is not accurately represented in the research record. Plagiarism is the appropriation of another person’s ideas, processes, results, or words without giving appropriate credit, including those obtained through confidential review of others’ research proposals and manuscripts. The principle of beneficence requires the researcher to do good and “above all, do no harm.” DIF: Cognitive Level: Application 16. A master’s student knows next to nothing about Maslow’s theory related to hierarchy of needs

but, on an advisor’s recommendation, decides to use it as a theoretical framework for the student’s thesis. The student goes to the library and accesses an old master’s thesis that also uses the theory and copies three pages, word for word. This student uses the other student’s reference to Maslow’s work. What word best describes this master’s student’s actions? a. Beneficence b. Fabrication c. Falsification d. Plagiarism ANS: D

Plagiarism is the appropriation of another person’s ideas, processes, results, or words without giving appropriate credit, including those obtained through confidential review of others’ research proposals and manuscripts. Fabrication in research is the making up of results and the recording or reporting of them. Falsification of research is manipulating research materials, equipment, or processes or changing or omitting data or results such that the research is not accurately represented in the research record. The principle of beneficence requires the researcher to do good and “above all, do no harm.” DIF: Cognitive Level: Application 17. A master’s student knows next to nothing about Maslow’s theory related to hierarchy of needs

but, on an advisor’s recommendation, decides to use it as a theoretical framework for the student’s thesis. The student goes online and finds a Wikipedia page, copying the description of Maslow’s theory verbatim, putting a citation at the end of the paragraph, but not using quotation marks. What word best describes this master’s student’s actions? a. Beneficence b. Fabrication c. Falsification d. Plagiarism ANS: D

Plagiarism is the appropriation of another person’s ideas, processes, results, or words without giving appropriate credit, including those obtained through confidential review of others’ research proposals and manuscripts. Fabrication in research is the making up of results and the recording or reporting of them. Falsification of research is manipulating research materials, equipment, or processes or changing or omitting data or results such that the research is not accurately represented in the research record. The principle of beneficence requires the researcher to do good and “above all, do no harm.” DIF: Cognitive Level: Application 18. A researcher receives permission to use the information in a hospital data set, without patient

identifiers. What level of participant consent is required? a. Partial: the participants must all be notified that their data are being reused. b. None. c. Partial: the participants must all be notified if the results are published. d. Full: all participants must be contacted and must agree to have their data used. ANS: B

Covered entities (healthcare provider, health plan, and healthcare clearinghouse) may use and disclose a limited data set to a researcher for a study without an individual participant’s authorization or an IRB waiver. DIF: Cognitive Level: Comprehension 19. A researcher is applying for Institutional Review Board (IRB) approval, and the form

specifies that the researcher indicate the probable level of risk. The research creates situations in which the participants, registered nurses, are placed in unusual code-like situations in which they do not know what action to take, and actors play the parts of other healthcare providers. The participants are then asked to describe their feelings in the scenarios, and their levels of confidence as they go through 15 scenarios. What level of risk does this study pose?

a. b. c. d.

No anticipated effects Temporary discomfort Unusual discomfort Risk of permanent harm

ANS: B

Studies that cause temporary discomfort are described as low-risk studies, in which the discomfort encountered is similar to what the participant would experience in his or her daily life and ceases with the termination of the study. Many nursing studies require the participants to complete questionnaires or participate in interviews, which usually involve minimal risk. Physical discomforts of such research might be fatigue, headache, or muscle tension. Emotional and social risks might entail the anxiety or embarrassment associated with responding to certain questions. Economic risks might consist of the time spent participating in the study or travel costs to the study site. Participation in many nursing studies is considered a mere inconvenience for the participant, with no foreseeable risks of harm. Most clinical nursing studies examining the impact of a treatment involve minimal risk. DIF: Cognitive Level: Comprehension 20. A physician is conducting research on a new and promising chemotherapy treatment for breast

cancer that improves survival and decreases adverse symptoms. Sixty participants will be recruited; of these, thirty will be assigned to the experimental group, receiving the new treatment, and thirty to the control group, receiving the usual chemotherapy. The physician’s wife, newly diagnosed with breast cancer, is randomly assigned to the control group; he removes her from the control group and places her in the experimental group. What ethical violation has occurred? a. The physician’s wife has a right to self-determination: her husband has decided her group assignment for her. b. The physician has no right to know anything about his wife’s breast cancer: this is a violation of confidentiality. c. The physician’s wife shouldn’t be a member of the study: it’s a conflict of interest. d. The physician’s wife has no right to be included in the experimental group: it unfairly excludes someone else from this special benefit. ANS: D

A concern with participant selection that is related to justice is that some researchers select certain people as participants because they like them and want them to receive the specific benefits of a study. Other researchers have been swayed by power or money to make certain individuals participants so that they can receive potentially beneficial treatments. It is especially important in research not to show preference in assigning participants. That is the benefit of random assignment: it is fair. DIF: Cognitive Level: Application 21. From an ethical point of view, what is the point of determining that a potential research

participant is incompetent? a. An incompetent participant must receive more extensive explanation before consenting to participate in research. b. According to HIPAA, a different level of records security must ensue. c. Inclusion of the participant necessitates a different consenting process. d. The researcher has a responsibility to exclude all incompetent persons from

research participation. ANS: C

about doing that, without involving coercion? a. Mention that participation provides extra points. b. Have a research assistant consent all participants and collect all data. c. Offer extra points to the whole class if 50% of them act as participants. d. Open the study to all students on campus and provide nonacademic incentives. ANS: D

A participant’s right to self-determination can be violated through covert data collection and deception. The right of self-determination may also be threatened when potential research participants are susceptible to coercion Students may feel forced to participate in research to protect their grades or prevent negative relationships with the faculty conducting the research. Opening the study to all students on campus would decrease the risk of coercion. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. A nurse plans to interview prisoners as part of the nurse’s master’s thesis on treatment of

health problems in correctional institutions. What special measures must the nurse take before studying these potential participants? (Select all that apply.) a. Justify to an Institutional Review Board why the nurse must use prisoners as participants. b. Devise a consent process that provides for a conservator’s signature. c. Destroy all of the nurse’s records. d. Devise interview questions that avoid any mention of prisons or prisoners. e. Bracket the nurse’s previous beliefs about prisoners. f. Assure that the consent process involves no coercion. ANS: A, F

The U.S. DHHS has identified certain vulnerable groups of individuals, including pregnant women, human fetuses, neonates, children, mentally incompetent persons, and prisoners, who require additional protection in the conduct of research. Researchers need to justify their use of participants with diminished autonomy in a study, and the need for justification increases as the participants’ risk and vulnerability increase. Participants with diminished autonomy may be subject to coercion. DIF: Cognitive Level: Analysis 2. Why are research ethics essential? (Select all that apply.)

a. b. c. d. e.

Research participants must be protected from accidental disclosure of information. Institutional Review Boards exist to protect patient rights. Researcher misconduct may result in dissemination of potentially harmful results. Results published in professional journals represent a clear violation of privacy. Research participants must be protected from deliberate violation of their rights.

ANS: A, C, E

Ethical research is essential for generating knowledge for practice. The ethical conduct of research has been a focus since the 1940s because of the mistreatment of human participants in selected studies. Human rights are claims and demands that have been justified in the eyes of an individual or by the consensus of a group of individuals. Having rights is necessary for the self-respect, dignity, and health of an individual. The human rights that require protection in research are (1) self-determination, (2) privacy, (3) anonymity and confidentiality, (4) fair treatment or justice, and (5) protection from discomfort and harm. Although Institutional Review Boards exist to protect patient rights, this is not a reason that research ethics are essential. Results published in professional journals do not represent a violation of privacy, if the researcher has attended to ethical mandates. DIF: Cognitive Level: Synthesis 3. An improvement in research ethics could prevent some or all of which of the following?

(Select all that apply.) a. Breaches of anonymity b. Researchers’ failures to report their funding sources in publications c. Minimal risk to research participants d. Unauthorized data collection e. Patients’ inability to understand complex research designs ANS: A, B, D

Ethical research is essential to generate sound knowledge for practice. The ethical conduct of research has been a focus since the 1940s because of the mistreatment of human participants in selected studies. Human rights are claims and demands that have been justified in the eyes of an individual or by the consensus of a group of individuals. Having rights is necessary for the self-respect, dignity, and health of an individual. The human rights that require protection in research are (1) self-determination, (2) privacy, (3) anonymity and confidentiality, (4) fair treatment or justice, and (5) protection from discomfort and harm. Although Institutional Review Boards exist to protect patient rights, this is not a reason that research ethics are essential. Results published in professional journals do not represent a violation of privacy, if the researcher has attended to ethical mandates. DIF: Cognitive Level: Synthesis 4. In order for consent to be voluntary, which must occur? (Select all that apply.) a. The participant must sign a consent form. b. The participant cannot be mentally incompetent. c. The participant cannot be shamed, forced, or cajoled into participation. d. The participant will not be paid (remunerated) because this would be coercive. e. The researcher must confirm that the person signing the consent form truly

understands what the research will involve. ANS: C, E

Voluntary consent means that the prospective participant has decided to take part in a study of his or her own volition without coercion or any unique influence. Voluntary consent is obtained after the prospective participant has been given essential information about the study and has shown comprehension of this information. In some studies, the consent form may be replaced by oral consent or the consent form may be used but the participant’s signature is waived. A person who is mentally incompetent or incapacitated may be a research participant, but his or her legal representative must consent for participation. If an individual is judged incompetent and incapable of consent, the researcher must seek approval from the prospective participant and his or her legally authorized representative. It is the researcher’s responsibility to confirm that the person signing the consent form truly understands what the research entails. Sometimes nursing studies have included a small financial reward of $10 to $30 or support for transportation to increase participation, but this would not be considered coercive. DIF: Cognitive Level: Analysis 5. Which of these statements concerning guidelines for consenting children for research

participation are true? (Select all that apply.) a. No infant or child may be used in research if he or she refuses treatment. b. Emancipated minors may consent for themselves. c. Coercion is wrong, but begging a child to participate is acceptable. d. An 11-year-old should be asked to assent for research participation. e. If infants and children participate in research, they should sign a consent form. f. Infants cannot refuse to participate in research if their parents consent. ANS: B, D, F

The unique vulnerability of children means that their safety must be balanced with the need for research to improve their care. Because of maturity levels, consent involving children must focus not only on assuring that they understand their rights, but upon comprehension of the study, as well. To that end, special ethical and regulatory considerations exist for research involving children. Federal regulations contain two stipulations for obtaining informed consent: the research must be of minimal risk, and both the assent of the child (when capable) and the consent of the parent or guardian must be obtained. A child who is no longer a minor can give consent. A child’s competency to assent is usually governed by age, and research evidence supports the standard of a child over 9 years of age being capable of sufficient understanding to give assent. DIF: Cognitive Level: Synthesis 6. The Tuskegee study was ethically objectionable because informed consent was flawed, an

available treatment was not provided, and deception was practiced. If informed consent had been properly administered and research participants informed of the availability of penicillin when it became available, why would this still represent an ethically objectionable study? (Select all that apply.) a. The researcher has an obligation to actively do good for the research participants; merely informing them of the availability of penicillin would not have been sufficient to meet this obligation. b. The research took place in one state of the Union and so had limited generalizability. c. Some of the research participants were illiterate and could not provide consent. d. There was no need for the study to be performed, in the first place, since enough

was known about syphilis at the time. e. Since black men in Alabama were in an inferior social position, they constituted an underrepresented and potentially vulnerable population; every effort should have been made to include participants from other ethnic groups. ANS: A, E

In 1932, the U.S. Public Health Service initiated a study of syphilis in black men in the small, rural town of Tuskegee, Alabama. The study, which continued for 40 years, was conducted to determine the natural course of syphilis in the black men. The research participants were organized into two groups: one group consisted of 400 men who had untreated syphilis, and the other was a control group of 200 men without syphilis. Many of the participants who consented to participate in the study were not informed about the purpose and procedures of the research. Some individuals were unaware that they were participants in a study. The participants with syphilis were examined periodically but were not ever administered penicillin, which became standard treatment for the disease in the 1940s. There was insufficient knowledge about the natural course of syphilis at the time the study was begun. Consent of illiterate participants does not prohibit consent. When likely that some participants may have limited reading ability, the researcher may read the consent aloud to all participants to avoid embarrassment. Single-site research is not considered ethically objectionable per se. DIF: Cognitive Level: Analysis 7. A researcher obtains consent from a person with a recent traumatic brain injury (TBI) to

observe the person and test her at intervals, using cognitive survey instruments. The person has not yet regained the ability to speak and can understand and obey only simple commands. She nods yes, and shakes her head for no. The participant’s husband is consented for the study, and the patient is asked to assent. Does this fulfill the requirements for consenting someone with diminished capabilities? Why or why not? (Select all that apply.) a. Yes, it does. b. No, it does not. c. The participant should have been told the purpose of the study over and over again, and the tests the researcher planned to administer, until the participant nodded that she understood. Her husband should not make this decision for her. d. The researcher must obtain consent from both the legal representative and the participant. e. The researcher need not obtain assent for research involving persons with decreased ability or total inability to give informed consent. The participant will probably not remember any of this later, anyhow. f. The participant should have been asked to consent, and the husband to assent. That is the proper procedure. g. The prospective participant can understand simple commands but, because of her TBI, she is not competent to consent. h. The participant is asked to assent, in case she has an opinion about this and might understand the purpose of the study. Eliciting her cooperation is wise, in either case. ANS: A, G, H

Some persons have diminished autonomy or are vulnerable and less advantaged because of legal or mental incompetence, terminal illness, or confinement to an institution. These persons require additional protection of their right to self-determination, because they have a decreased ability, or an inability, to give informed consent. In addition, these persons are vulnerable to coercion and deception. Neonates and children (minors), the cognitively impaired, and unconscious patients are legally or mentally incompetent to give informed consent. They should, however, be asked to assent, since their cooperation is essential for high-quality data collection. If an individual is judged incompetent and incapable of consent, the researcher must seek approval from the prospective participant and his or her legally authorized representative. DIF: Cognitive Level: Analysis 8. In the Jewish Chronic Disease Hospital Study, 22 patients were injected—unknowingly—with

a suspension containing live cancer cells that had been generated from human cancer tissue. What ethical principles apply here? (Select all that apply.) a. Beneficence b. Self-determination c. Anonymity d. Confidentiality e. Fair treatment ANS: A, B, E

A highly publicized example of unethical research was a study conducted at the Jewish Chronic Disease Hospital in the 1960s. Its purpose was to determine the patients’ rejection responses to live cancer cells. Twenty-two patients were injected with a suspension containing live cancer cells that had been generated from human cancer tissue. An extensive investigation revealed the patients were not informed that they were research participants. They were informed that they were receiving an injection of cells, but the word cancer was omitted. In addition, the Jewish Chronic Disease Hospital’s institutional review board never reviewed the study. The physician directing the research was an employee of the Sloan-Kettering Institute for Cancer Research, and there was no indication that this institution had reviewed the research project. The principle of beneficence requires the researcher to do good and “above all, do no harm.” DIF: Cognitive Level: Application 9. Thuy is a nurse researcher. She completes her paperwork for the Institutional Review Board

(IRB). Her application for approval is returned to her, with comments as to how it should be revised and resubmitted. Which of the following comments are within the scope of the IRB? (Select all that apply.) a. “You have failed to provide a copy of your survey. Please do so.” b. “Your study protocol does not provide information on potential risks to anonymity. Please indicate this in Section 1g.” c. “Because of inexperience in this area, the IRB invites you to meet with us as one of the reviewers of this protocol.” d. “We can only provide provisional approval of your study.” e. “You have not included information about the risk-to-benefit ratio of this research. Please do so.” ANS: A, B, E

An institutional review board (IRB) is a committee that reviews research to ensure that all investigators are conducting research ethically. All hospital-based research must be submitted to the hospital’s IRB, which will then determine whether it is high risk, moderate risk, minimal risk, or exempt from review. Universities, hospital corporations, and many managed care centers maintain IRBs to promote the conduct of ethical research and protect the rights of prospective participants at these institutions, as required since 1974. Each IRB has at least five members of various backgrounds (e.g., cultural, economic, educational, gender, racial) to promote a complete, scholarly, and fair review of research that is commonly conducted in an institution. If an institution regularly reviews studies with vulnerable participants, such as children, neonates, pregnant women, prisoners, and mentally disabled persons, the IRB should include one or more members with knowledge about and experience in working with these individuals. The members must have sufficient experience and expertise to review a variety of studies, including quantitative, qualitative, and mixed methods research. Any IRB member who has a conflict of interest with a research project being reviewed must excuse himself or herself from the review process, except to provide information requested by the IRB. In reviewing the research, the reviewers may exercise all of the authorities of the IRB such as require revision of a study protocol or study documents and disapproval of the research. DIF: Cognitive Level: Application 10. Which of the following statements are true? (Select all that apply.) a. HIPAA regulations were formulated to address ethical treatment of research b. c. d. e.

participants. If electronic medical records had not been invented, HIPAA would not have been necessary. Data held by health insurance companies sparked the emergence of HIPAA. Ethics and HIPAA regulations overlap in the area of justice. Ethics and HIPAA regulations overlap in the area of anonymity.

ANS: B, C, E

One of the more recent regulations, the Health Insurance Portability and Accountability Act (HIPAA), was enacted in 2003 to protect the privacy of an individual’s health information. In addition, the concern for patient privacy with the electronic storage and exchange of health information has resulted in HIPAA privacy regulations. The principle of justice holds that human subjects should be treated fairly. Anonymity exists if the participant’s identity cannot be linked, even by the researcher, with his or her individual responses. DIF: Cognitive Level: Synthesis 11. Research articles may be considered fraudulent in which of the following instances? (Select

all that apply.) a. The person who designed the study and performed all of the research is not mentioned as an author. b. The authors hired someone other than themselves to collect, analyze, and interpret the data. c. Graduate students collected the data but did not analyze it. d. A statistician was hired to perform all of the statistical tests. e. Both quantitative and qualitative results were reported in the same article. f. The authors used another researcher’s raw data without permission. ANS: A, B, F

Editors of journals have a major role in monitoring and preventing research misconduct in the published literature. The World Association of Medical Editors has identified data falsification, plagiarism, and violations of legal and regulatory requirements as some types of scientific misconduct. Authors who are primary investigators for research projects must be responsible in their conduct and the conduct of their team members, from data collection through publication of research. Coauthors and coworkers should question and, if necessary, challenge the integrity of a researcher’s claims. Sometimes, well-known scientists’ names have been added to a research publication as coauthors to give it credibility. Individuals should not be listed as coauthors unless they were actively involved in the conduct and publication of the research. Similarly, supervisors and directors of hospital units should not be included as last author as a “courtesy” for a publication unless they were actively involved in at least one phase of the research. DIF: Cognitive Level: Evaluation 12. A breach in confidentiality occurs. Which of the following represent a breach in

confidentiality? (Select all that apply.) a. The teenaged son of a researcher reads some of the raw interview data on the researcher’s computer. b. The researcher accidentally includes the real names of one participant’s husband and two daughters in the finished article, instead of changing these to pseudonyms. c. A researcher presents her findings at a research conference. d. A tape of a research interview is misplaced in the researcher’s home, and is never found. e. The researcher mentions to a colleague that all of the participants in a recent research project on anger were divorced women. ANS: A, B, D

A breach of confidentiality can occur when a researcher, by accident or direct action, allows an unauthorized person to gain access to a study’s raw data. Confidentiality can be breached in the reporting or publishing phases of a study in which a participant’s identity is accidentally revealed, violating the participant’s right to anonymity. Breaches can harm participants psychologically and socially, as well as destroy the trust they had in the researcher who promised confidentiality. Breaches can be especially harmful to a research participant when they involve religious preferences, sexual practices, employment, personal attributes, or opinions that may be considered positive or negative, such as racial prejudices. DIF: Cognitive Level: Comprehension 13. A researcher conducts a mixed methods study on exercise as a modality of controlling

hyperglycemia. The study has both quantitative results, describing the amount that glucose falls with various amounts of exercise, and qualitative results, describing participants’ mood and sense of well-being with different kinds of exercise. The researcher decides to publish an article based on the quantitative findings immediately but wait to publish the qualitative results later. What are the reasons that this would not be an instance of researcher misconduct? (Select all that apply.) a. The data from the quantitative part of the study are reported completely and honestly. b. The journal does not accept qualitative research. c. Both “arms” of the study are free-standing: reporting only the quantitative results

does not misrepresent the findings. d. Nobody will know that a qualitative study was performed. e. No denial of the full scope of data collection is made. ANS: A, C, E

Research misconduct is defined as “the fabrication, falsification, or plagiarism in processing, performing, or reviewing research, or in reporting research results. It does not include honest error or differences in opinion.” Fabrication in research is the making up of results and recording or reporting them. Falsification of research is manipulating research materials, equipment, or processes, or changing or omitting data or results such that the research is not accurately represented in the research record. The data from this study were neither fabricated nor falsified; it is the researcher’s decision when to disseminate research results. DIF: Cognitive Level: Evaluation 14. Which one of the following are considered vulnerable populations, from an ethical point of

view? (Select all that apply.) a. Students b. Persons with osteoporosis who are subject to hip fracture c. Persons who are depressed d. Prisoners e. Persons who have recently suffered loss of a spouse ANS: A, D

Some persons have diminished autonomy or are vulnerable and less advantaged because of legal or mental incompetence, terminal illness, or confinement to an institution. These persons require additional protection of their right to self-determination, because they have a decreased ability, or an inability, to give informed consent. In addition, these persons are vulnerable to coercion and deception. The U.S. DHHS has identified certain groups of individuals who require additional protection in the conduct of research, including pregnant women, human fetuses, neonates, children, mentally incompetent persons, and prisoners. Sometimes students feel forced to participate in research to protect their grades or prevent negative relationships with the faculty conducting the research. DIF: Cognitive Level: Analysis 15. Why are vulnerable populations considered vulnerable? To what are they vulnerable? (Select

all that apply.) a. Physical harm because of a preexistent mental or physical condition b. The possibility of being assigned to the experimental group c. Unethical researchers d. Coercion e. Diminished autonomy because of an impaired ability to consent ANS: A, D, E

Some persons have diminished autonomy or are vulnerable and less advantaged because of legal or mental incompetence, terminal illness, or confinement to an institution. These persons require additional protection of their right to self-determination, because they have a decreased ability, or an inability, to give informed consent. In addition, these persons are vulnerable to coercion and deception. The U.S. DHHS has identified certain groups of individuals who require additional protection in the conduct of research, including pregnant women, human fetuses, neonates, children, mentally incompetent persons, and prisoners. Some of these hospitalized patients are survivors of trauma (such as auto accidents, gunshot wounds, or physical and sexual abuse) who are very vulnerable and often have decreased decision-making capacities. Sometimes students feel forced to participate in research to protect their grades or prevent negative relationships with the faculty conducting the research. Other participants are coerced to participate in studies because they believe that they cannot refuse the excessive rewards offered, such as large sums of money, specialized health care, special privileges, and jobs. DIF: Cognitive Level: Analysis

Chapter 10: Quantitative Methodology: Noninterventional Designs and Methods Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. Which one of the following research approaches tests causality? a. Grounded theory b. Experimentation c. All quantitative research d. Correlational research ANS: B

Quantitative research may be interventional or noninterventional. Causality refers to a cause-and-effect relationship, in which one variable causes a change in another. Interventional research tests the stated or implied hypothesis of a cause-and-effect relationship between variables, in which a researcher enacts an intervention that causes a change in the dependent variable. The two types of interventional research discussed in this text are experimental and quasi-experimental. Interventional research always has a research hypothesis, either stated or implied. Non-interventional research is divided into descriptive designs and correlational designs. DIF: Cognitive Level: Comprehension 2. Why is selection of an appropriate design for a Non-interventional research study important? a. If the design is an incorrect one, the researcher will examine variables and their

interactions in a way that does not answer the research question. b. The design involves a choice between quantitative, qualitative, outcomes, or mixed

methods research. c. All designs should include data collected across time. d. If the design is appropriate, the researcher can eliminate error. ANS: A

The research methodology represents the major type of research used for a study. Within nursing research, methodology’s types are quantitative, qualitative, outcomes, and mixed methods. Research design is the researcher’s choice of the best way in which to answer a research question, with respect to several considerations, including number of participant groups, timing of data collection, and researcher intervention, if any. Measurements always contain a certain amount of error. Time-dimensional designs are used extensively within the discipline of epidemiology, to examine change over time, but not all Non-interventional designs are time-dimensional. DIF: Cognitive Level: Analysis 3. Random selection of 300 participants yields a sample. Demographic analysis of that sample

reveals that there are 99 teachers in the sample, despite the fact that the target population contains far fewer than 33% teachers. Which term describes the sample? a. Biased b. Controlled c. Multicausal d. Fully manipulated

ANS: A

The term bias means to slant away from the true or expected. A biased opinion has failed to include both sides of the question. Participants selected may not represent a population well, introducing bias into the analysis. Control in research design means control of potentially extraneous variables. Multicausal refers to the case in which two or more variables combine in causing an effect. It refers to the quantitative researcher’s action of changing the value of the independent variable, in order to measure its effect on the dependent variable. Researcher manipulation is always present in interventional research, but never present in Non-interventional research. DIF: Cognitive Level: Application 4. If a researcher plans to study graduate-level achievement in all students who were educated

under the Vermont public school system, in a small town that used both state-mandated texts and enrichment texts of the school board’s choosing, the researcher would be using a fairly small sample, bound by geography and time. Which type of validity is decreased by a study like this one? a. Construct validity b. Statistical conclusion validity c. External validity d. Internal validity ANS: C

External validity is the extent to which study findings can be generalized beyond the sample included in the study. It reflects design-resultant decisions that determine the population to which research results can be generalized. Construct validity in quantitative research relates to whether a study measures all aspects of the concepts it purports to measure. Internal validity is an assessment of the degree to which the measured relationships among variables are truly due to their interaction and the degree to which other intrusive variables might have accounted for the measured value. Statistical conclusion validity is the degree to which the researcher makes decisions about proper use of statistics, so that the conclusions about relationships and differences drawn from the analyses are accurate reflections of reality. DIF: Cognitive Level: Analysis 5. How does a comparative descriptive design differ from a typical descriptive design? a. It compares statistics between the current time and an earlier time, whereas the

typical descriptive design focuses on only one time period. b. It compares a number of variables and examines the relationship between them,

whereas a typical descriptive design never does this. c. It differs in name only; both have the same design. d. It describes data from two different groups, whereas a typical descriptive design

focuses on a single group. ANS: D

A research question of “What is?” or “To what degree?” often can be answered quite adequately using a descriptive design, sometimes called a simple descriptive design. Exactly as in simple descriptive research, the purpose of the comparative descriptive design is to describe, to answer the question of “What is?” or “To what degree?” The difference between the two designs, however, is that in comparative descriptive research two distinct groups are described and compared, in terms of their respective variables. A correlational design describes relationships between variables. DIF: Cognitive Level: Analysis 6. Why is the threat of participant attrition more problematic in longitudinal designs than in

other types of descriptive research? a. Participants are elderly. b. Data analysis is complex, and missing data points necessitate dropping the participant from the analysis. c. Data collection occurs over a much longer period of time. d. Treatments are aversive, making participants in the experimental group drop out. ANS: C

The subject attrition threat to design validity is due to subjects who drop out of a study before completion. Longitudinal designs examine changes in the same participants over time. In prospective longitudinal research, samples must be relatively large, because attrition over time is expected. DIF: Cognitive Level: Analysis 7. What do cross-sectional designs, trend designs, and longitudinal designs have in common? a. They all study participants at one time. b. They all focus on change over time. c. They all involve data collection over months or years. d. They are identical to ordinary descriptive designs. ANS: B

Time-dimensional designs are used extensively within the discipline of epidemiology, to examine change over time, in relation to disease occurrence. Within Non-interventional research, there are two principal types of time-dimensional studies: (1) longitudinal research and (2) cross-sectional research. Either of these can be descriptive or correlational in type. Both types of time-dimensional research can be conducted either retrospectively or prospectively. DIF: Cognitive Level: Synthesis 8. Several television programs, such as those with an amateur performance component, allow

viewers to text in votes for their favorite performer. From a research point of view, this is what kind of a design? a. Simple descriptive b. Comparative descriptive c. Longitudinal d. Simple correlational ANS: A

Descriptive research is conducted in a natural setting to answer a research question related to incidence, prevalence, or frequency of occurrence of a phenomenon of interest and its characteristics. It describes the phenomenon of interest and its component variables, within one single participant group. In comparative descriptive research two distinct groups are described and compared. Longitudinal research examines change in a variable over time, within a defined group. Correlational research is conducted to establish the direction and the strength of relationships between or among variables, as they exist in a natural setting. DIF: Cognitive Level: Application 9. Structural equation modeling (a type of model-testing research) uses large samples. What is

the reason for this? a. Interactions among many variables are tested. b. The research is experimental, so a large, multi-site sample is preferred. c. Causation cannot be demonstrated in a small sample. d. Differences often are minuscule, because the sample is homogeneous, and so the effect size is small. ANS: A

Structural equation modeling (SEM) tests theoretical relationships within a model. Its complex calculations, however, also allow the researcher to identify the best model that explains interactions among variables, yielding the greatest explained variance. SEM is capable of analyzing models with two-way paths between variables, as well as determining how three or more variables interact, using multiple regression analysis. Because a number of variables may be examined in such research, samples must be large enough to provide statistical power. Previously, the rule of thumb was that ten participants were required for each variable tested. With model-testing, however, the sample must be even larger because statistical relationships are complex, multilevel, and interacting. Researchers conducting studies for model-testing use large samples. DIF: Cognitive Level: Synthesis 10. Researchers studied alcoholism recovery, comparing the success rate for two groups of

participants: those receiving individual psychotherapy and those not receiving individual psychotherapy. The researchers measured sobriety once, at 18 months’ posttreatment initiation. What study design would be most suitable for this type of research project? a. Longitudinal descriptive design b. Comparative descriptive design c. Cross-sectional design d. Model-testing design ANS: B

In longitudinal designs, data are collected repeatedly at intervals in a single cohort, over a period of time, not only at end point. In comparative descriptive designs, two or more distinct groups are described and compared, in terms of their respective variables. Cross-sectional designs examine change over time by collecting data from different groups of participants in various stages of a process, with all data collected at about the same time. Model-testing designs use correlational research for measurement of proposed relationships within a theoretical model. DIF: Cognitive Level: Analysis

11. A researcher conducts a correlational study to determine the relationship between strict

discipline in one’s home of origin and anxiety disorders. At the beginning of the study the researcher defines the study variables, both conceptually and operationally. Which type of validity demands careful definition of study variables? a. Construct validity b. Internal validity c. External validity d. Statistical conclusion validity ANS: A

Construct validity in quantitative research relates to whether a study measures all aspects of the concepts it purports to measure. This is a direct result of how well the researcher has conceptually defined and then operationalized a study’s variables. Internal validity is an assessment of the degree to which the measured relationships among variables are truly due to their interaction and the degree to which other intrusive variables might have accounted for the measured value. External validity is the extent to which study findings can be generalized beyond the sample included in the study. Statistical conclusion validity is the degree to which the researcher makes decisions about proper use of statistics, so that the conclusions about relationships and differences drawn from the analyses are accurate reflections of reality. DIF: Cognitive Level: Application 12. Hospital nurses are observed in order to determine exactly how long nurses at a major urban

hospital swab IV ports with alcohol. The researcher chooses to observe nurses in a high-acuity emergency department within that hospital. Because the nurses often are in near-code circumstances, they “scrub the hub” only as long as they have time to do so. Collecting data exclusively from this high-acuity unit is an example of what concept, relevant to quantitative research? a. Causality b. Control c. Retrospective design d. Bias ANS: D

The term bias means to slant away from the true or expected. Collecting data only in one unit of the hospital may present a biased view of what nurses do, hospital-wide, especially because of the very high acuity of that area. Causality refers to a cause-and-effect relationship. Interventional research tests the stated or implied hypothesis of a cause-and-effect relationship between variables, in which a researcher enacts an intervention that causes a change in the dependent variable. Non-interventional research describes variables as they exist, sometimes examining the relationship or association between variables but never establishing causality. Control in research design means control of potentially extraneous variables. Retrospective research collects data from preexistent data sources. This hospital study involved observational data, collected by the researcher. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE

1. A researcher designs a study that tallies how many days the schoolchildren living in Illinois

must stay inside at recess because of inclement weather. The researcher’s intent is to generalize study findings to all public schools in Illinois, as a justification for a larger and better indoor multipurpose room for any new or remodeled schools in the state. What strategies on the part of the researcher would help achieve this level of generalizability? Assume that all schools in the sample will receive a copy of the plans for the study, with a statement emphasizing the possible benefits to the area schools through participation in the study. (Select all that apply.) a. The researcher will not allow any school to decline to participate in the study. b. The researcher will select a large sample of schools randomly from all schools in Illinois. c. The researcher will send a questionnaire to every school in Illinois. d. The researcher will promise participating schools that they will be first in line for monetary rewards to enhance their schools’ multipurpose rooms. e. The researcher will choose 200 target schools in the state that average the highest percentage of instructional days affected by inclement weather. ANS: B, C, E

Coercion occurs when one person intentionally presents another with an overt threat of harm or the lure of excessive reward to obtain his or her compliance. Participants may refuse to participate without loss of status or quality of care. External validity is the extent to which study findings can be generalized beyond the sample included in the study. It reflects design-resultant decisions that determine the population to which research results can be generalized. External validity is due, in large part, to sampling strategy, because the population to which results can be generalized is the population represented by the sample. Selecting a large random sample allows generalization of study findings to the population. When a sample consists of almost the entire accessible population, results can be generalized to the target population when the sample is representative. DIF: Cognitive Level: Analysis 2. What are the desired outputs of model-testing designs? (Select all that apply.) a. Evidence that for all future participants the relationships in the model will hold

true b. Identification of which ones of a group of variables are associated with a given

outcome c. Elimination of possible terms in the model that are found not to be statistically significant d. Establishment of a working theoretical model for a process e. Proof of causation ANS: B, C, D

Model-testing designs use correlational research for measurement of proposed relationships within a theoretical model. Its complex calculations, however, also allow the researcher to identify the best model that explains interactions among variables. In model-testing designs, the researcher sets the level of statistical significance. Relationships that are within that level, the stronger relationships, are retained in the model. Relationships that are weaker than the set point (greater than the p-level set by the researcher) are removed from the model. The model may involve correlation, proposed causation, or both. If a model with causative elements is supported by model-testing research, the model can provide the framework for subsequent interventional study. Tests of correlation, even if strongly positive, do not establish causation. Causality and correlation are distinctly different. Causality refers to a cause-and-effect relationship, in which one variable causes a change in another. Interventional research tests the stated or implied hypothesis of a cause-and-effect relationship between variables, in which a researcher enacts an intervention that causes a change in the dependent variable. Non-interventional research describes variables as they exist, sometimes examining the relationship or association between variables but never establishing causality. DIF: Cognitive Level: Analysis 3. Correlational research has which of the following characteristics? (Select all that apply.) a. Examines the strength of a relationship, to determine causality b. Allows independent variables to be manipulated c. Examines relationships among existing variables d. Is used to generate rather than test hypotheses e. Always uses large samples f. Can test a model ANS: C, F

Causality and correlation are distinctly different. Causality refers to a cause-and-effect relationship, in which one variable causes a change in another. Interventional research tests the stated or implied hypothesis of a cause-and-effect relationship between variables, in which a researcher enacts an intervention that causes a change in the dependent variable. Non-interventional research describes variables as they exist, sometimes examining the relationship or association between variables but never establishing causality. Correlational research may have a hypothesis. In Non-interventional research, a researcher does not enact an intervention, in order to measure its effect: in Non-interventional research, all that a researcher does is classify, count, measure, and retrieve data. Because a number of variables may be examined in model-testing research, a correlational strategy, samples must be large enough to provide statistical power. Qualitative grounded theory research generates hypotheses; quantitative research tests them. DIF: Cognitive Level: Comprehension 4. A hospital manager reviews the past year’s charting to determine what kind of oral care

patients have actually been receiving, who has been delivering the oral care, and oral care’s relationship with infection of all sources. This study could be which of the following? (Select all that apply.) a. Prospective b. Retrospective c. Correlational d. Descriptive

e. Quasi-experimental ANS: B, C, D

Prospective is a term that means looking forward, whereas retrospective means looking backward, usually in relationship to time. Within research studies, these terms are used most frequently to refer to the timing of data-collection. Are the data obtained in “real time,” with measurements being obtained by the research team, or are the study’s data retrieved from data collected at a prior time for a different purpose? Correlational research examines relationships between and among variables. Descriptive research is conducted in a natural setting to answer a research question related to incidence, prevalence, or frequency of occurrence of a phenomenon of interest and its characteristics. Quasi-experimental research is interventional: it examines the effect of a researcher intervention. DIF: Cognitive Level: Synthesis 5. Researchers study 54 nonsmoking women with stage IV non–small cell lung cancer, for the

purpose of describing the women’s progress in response to standard treatment, which all of them receive. Which of the following designs would be suitable for this study? (Select all that apply.) a. Comparative descriptive b. Time-dimensional c. Prospective cohort d. Cross-sectional e. Predictive correlational f. Longitudinal g. Simple descriptive ANS: B, C, D, F

Descriptive research is conducted in a natural setting to answer a research question related to incidence, prevalence, or frequency of occurrence of a phenomenon of interest and its characteristics. The purpose of simple descriptive research is to describe the phenomenon of interest and its component variables, within one single participant group, sometimes called a cohort. Exactly as in simple descriptive research, the purpose of the comparative descriptive design is to describe, to answer the question of “What is?” or “To what degree?” The difference between the two designs, however, is that in comparative descriptive research two or more distinct groups are described and compared, in terms of their respective variables. Time-dimensional designs are used extensively within the discipline of epidemiology, to examine change over time, in relation to disease occurrence. Longitudinal designs examine changes in the same participants over time. A trend design is a variation of the longitudinal design. It is used extensively in epidemiology to examine changes across time in incidence, usually incidence of disease. Measurements in trend designs occur at similarly spaced intervals—monthly, yearly, or every 5 years, for instance. As in longitudinal designs, measurements are made at intervals, but in trend designs a somewhat different sample from the population is selected each time that data are collected. Samples usually are large, sometimes entire populations, and the sole aim is to measure incidence of one or more related variables, within that population. Cross-sectional designs examine change over time but, in order to do so, they collect data from different groups of participants in various stages of a process, with all data collected at about the same time. Prospective is a term that means looking forward, whereas retrospective means looking backward, usually in relationship to time. Within research studies, these terms are used most frequently to refer to the timing of data collection. DIF: Cognitive Level: Analysis 6. Predictive correlational studies are designed to provide a way to predict the value of one

variable, in relation to another variable. Which of the following research studies are predictive correlational in design? (Select all that apply.) a. One that studies the relationship of hospital admission blood alcohol level in chronic alcoholics to the amount of time that elapses before delirium tremens begin b. One that classifies patients coming to an emergency department as critically ill, acutely ill, or not acutely ill c. One that quantifies the probability that adolescents completing a one-day type I diabetes workshop will develop ketoacidosis in the following year d. One that studies both girls and boys in grammar school and counts the number of interactions they have with one another daily e. One that describes the incidence of postterm labor in all counties of New York state f. One that measures the effect of a researcher-applied independent variable upon a dependent variable ANS: A, C

The predictive correlational design is used to establish strength and direction of relationships between or among variables, with the intention of predicting the value of one of the variables, based on the value of the other variable(s). DIF: Cognitive Level: Application

7. Which of the following are potential sources of bias when conducting a research study?

(Select all that apply.) a. A random number table b. The research assistant’s belief that people with a certain hair color are illogical c. The statistician’s level of precision when inputting data d. The sample characteristics e. A 15-item scale that quantifies intrapartal depression f. A blood pressure cuff that has been properly calibrated ANS: B, C, D, E, F

The term bias means to slant away from the true or expected. In common parlance, it refers to a point of view that differs from truth; it slants away from the square, the objective, the balanced, leaning to one side. In designing research, it is important to be aware of bias emanating from decisions made during this phase of the study, because many aspects of the design process are subject to bias. The researcher can hold a biased view. Measurements made can lean in a certain direction. For example, systematic error occurs when a scale is not calibrated correctly and all measurements are skewed by the same amount. Participants selected may not represent a population well, introducing bias into the analysis. The research assistant assigning a number to participants’ behaviors may rate some individuals higher than others for reasons of personal bias such as preconception, perceptual problems, poor technique, and fatigue. Measurements always contain a certain amount of error, as well, even when devices are properly calibrated. This is why replication of results is so essential in increasing believability. DIF: Cognitive Level: Application 8. A researcher analyzes the past 3 years of patterns of hospital admissions, mortality, and

primary diagnosis, drawing from the admission department’s database. What kind of research could this be? (Select all that apply.) a. Prospective b. Retrospective c. Cross-sectional d. Longitudinal e. Descriptive f. Correlational g. Predictive h. Trend design ANS: B, C, D, E, F, G, H

Prospective is a term that means looking forward, whereas retrospective means looking backward, usually regarding whether data were obtained in “real time,” with measurements being obtained by the research team, or obtained from information collected at a prior time. Since the researcher is drawing from a database, this is a retrospective study. Descriptive research describes the phenomenon of interest and its component variables. This research examines hospital admissions, in addition to mortality and primary diagnosis, its component variables. Correlational research describes the relationships among the variables, and it is possible that the researcher might do this. Some correlational research identifies predictor variables: it is possible that the researcher will attempt to do this. Longitudinal designs examine changes in the same participants over time. If the “participant” of research is the hospital or the hospital’s units, this design could be said to be longitudinal. A trend design is a variation of the longitudinal design. It is used extensively in epidemiology to examine changes across time in incidence, usually incidence of disease, which is a focus of this particular study. Cross-sectional research examines change over time by collecting data from different groups of participants in various stages of a process. This might be the design if the researcher is attempting to identify changing trends over time, perhaps in relation to season of the year or economic conditions in the community. DIF: Cognitive Level: Analysis 9. A theoretical model is developed through qualitative research. The model explains family

dynamics in relation to a new leukemia diagnosis for an infant. The researcher now tests the model, using structural equation modeling (SEM). The final model contains family size, parental age, availability of extended family support, economic status, insurance status, and parental religious beliefs, as they predict anger, depression, effective decision-making, parental self-care, and cohesion. Which of the following are true, in relation to the model’s variables? (Select all that apply.) a. Parental religious belief is an exogenous variable. b. Leukemia diagnosis is an exogenous variable. c. Extended family support is an endogenous variable. d. Insurance status is an exogenous variable. e. Effective decision-making is an endogenous variable. f. Residual is NOT represented by any of the following: family size, parental age, availability of extended family support, economic status, and insurance status. ANS: A, D, E, F

Exogenous refers to variables chosen by the researcher to be included in the model, based on information found in the literature, existent theory, or the researcher’s experience. Exogenous variables’ values influence the values of other variables in the model. Exogenous factors’ own causes are not explained by the model. Endogenous refers to variables whose values are influenced, and possibly caused, by exogenous variables and other endogenous variables within the model. The “residual” refers to effects of variables, some unmeasurable or even unknown, which are not included in the final model. DIF: Cognitive Level: Application

10. A researcher surveys patients at various points of their hospitalizations, relative to the quality

of hospital food, measured on a scale that includes taste, texture, amount, temperature, and general appearance. Demographic data collected include age, gender, ethnicity, income, and family information, plus dates of admission and discharge for each patient. Variables related to food include individual items’ protein, fat, and calorie content, a self-rating of appetite at three points of the day, special diet requirements, and type of diet eaten at home. The researcher uses multiple regression analysis to make sense of the copious data. The number of hours that elapse between survey completion and hospital discharge seem to be the strongest predictor of quality of hospital food. Which three of the following statements are most likely explanations of this finding, considering the study’s Non-interventional design? (Select all that apply.) a. Nurses don’t treat patients who are close to going home as sick people and are more likely to encourage them to try to eat, which improves their appetites. b. As hospital discharge nears, patients feel better and their appetites improve. c. As hospital discharge nears, patients are increasingly ambulatory and expend more calories, improving their digestion and their appetite. d. Patients who are close to leaving the hospital receive decreasing amounts of opioid medication and, consequently, their appetites are less suppressed. e. Being surveyed about eating causes patients to be hungry. f. As hospital discharge nears, hospital workers are less likely to be sympathetic to patients’ complaints; this causes them to increase their oral intake. ANS: B, C, D

Non-interventional designs count and measure characteristics about the phenomenon of interest and the study’s variables, as they exist naturally, without researcher intervention. Non-interventional research describes variables as they exist, sometimes examining the relationship or association between variables but never establishing causality. Since they do not include interventions, the results of Non-interventional research, such as this correlational study, should be interpreted in terms of correlation, not causation. DIF: Cognitive Level: Application

Chapter 11: Quantitative Methodology: Interventional Designs and Methods Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. Hospital nurses are observed in order to determine exactly how long they swab IV ports with alcohol. Because they are being observed, they “scrub the hub” longer than they ordinarily would have. This is an example of what concept relevant to quantitative research? a. Bias b. Control c. Manipulation d. Hawthorne effect ANS: D The Hawthorne effect is a threat to construct validity, in which participants alter their normal behaviors because they are being scrutinized. This is also referred to as reactivity. The Hawthorne effect can exist in both non-interventional and interventional studies. Manipulation in interventional research means that the researcher enacts an intervention that alters the value of the independent variable, then measures its effect on one or more dependent variables. Control in research design means control for the effects of potentially extraneous variables, a serious issue for interventional research. Exerting control means either eliminating the effect of an extraneous variable or measuring its effect on the dependent variable. Bias refers to a point of view that differs from truth—it slants away from the square, the objective, the balanced, leaning to one side. DIF:

Cognitive Level: Analysis

2. A study using the factorial design measures the effect upon hemoglobin levels of four independent variables, each administered randomly and independently. How many distinct groups are there in this factorial design? a. 4 b. 8 c. 12 d. 16 ANS: D The factorial design is the classic experimental design with the addition of at least one additional independent variable that is also randomly assigned. In this way, the individual effect of either one of the variables, as well as the combined effect of the two independent variables, can be measured. A factorial design tests for multiple causality using two or more independent variables. This is the way it works for two independent variables. Subjects are randomly assigned to one of four groups: A receives both variables, B receives one variable, C receives the other variable, and D is the control group and receives neither variable. This is a “2  2” design, referring to the diagram of the four groups, and is the simplest form. More involved factorial experiments are possible. For instance, using three variables with two values each would produce eight different groups. The researcher also can examine an additional level of the independent variables, for instance using two variables with four values each, none-small-medium-large, yielding 16 different groups, as displayed below: M N O P Variables

Group 1 Group 2 Group 3 Group 4 Group 5 Group 6 Group 7 Group 8 Group 9 Group 10 Group 11 Group 12 Group 13 Group 14 Group 15 Group 16 DIF:

+ + + + + + + + -

+ + + + + + + +

M, N, O M, O M, N M N, O O N None M, N, O, P M, O, P M, N, P M, P N, O, P O, P N, P P

Cognitive Level: Evaluation

3. A researcher measures the dependent variable in an interventional group of subjects both before and after an intervention. The researcher also measures the same dependent variable in a non-interventional group, at the same two points in time. The groups are not randomly assigned. What kind of design is this? a. One-group pretest-posttest design b. Factorial design c. Pretest-posttest design with a comparison group d. Time series design with nonrandom control group ANS: C The pretest-posttest design with a comparison group is a commonly used quasi-experimental design. The researcher identified a group to whom the treatment will be administered and then identified another group with similar characteristics to serve as the comparison group. All participants complete the pretest, the treatment group receives the intervention, and all participants complete the posttest. Ideally, the groups’ mean scores on the pretest are not significantly different. The researcher will also compare the groups’ demographic characteristics and other variables that might influence the posttest scores, such as disease status or time since diagnosis. DIF:

Cognitive Level: Analysis

4. Nurses who provide discharge teaching to patients after colonoscopy call these patients the day after the procedure to check on their status. At that time, patients who have had polyps removed invariably ask how long it will be until they receive their results. The nurses decide to design a study in which they will change their discharge teaching, in order to include information about the time frame for biopsy results. The nurses then will measure patient satisfaction results, comparing them with the results for the previous month, before the change. Which type of research design will they use? a. Correlational b. Quasi-experimental

c. Experimental d. Descriptive ANS: B Interventional designs are those designs in which the researcher introduces an environmental condition, educational program, or different medication to determine its effect. Interventional research includes both experimental and quasi-experimental designs. The intent of the study is to examine the effect of an intervention; thus, only quasi-experimental or experimental designs are appropriate. The ability of the design to accomplish this purpose depends on the extent to which the actual effects of the experimental treatment (the independent variable) can be detected by measuring the dependent variable. Because data collection will not occur simultaneously in both groups, the study cannot use random assignment to group, which means that it is quasi-experimental, not experimental. DIF:

Cognitive Level: Application

5. If a one-group pretest-posttest study uses subjects as their own controls, which is the study design? a. Experimental b. Quasi-experimental c. Correlational d. Descriptive ANS: B Quasi-experimental and experimental designs examine causality. These two designs examine the effects of an intervention by comparing differences between groups that have received the intervention and those that have not received the intervention. This study lacks the presence of a distinct control group. Consequently, it is quasi-experimental in design. DIF:

Cognitive Level: Comprehension

6. A group of 25 Labrador retrievers, and their owners, are brought to the research lab, one at a time. The Labrador retrievers are shown various stimuli, including a squirrel that runs along a wire at the top of the lab, to elicit barking. Then the owners command the dogs to stop barking, and the stimulus is repeated. The duration of barking is measured. Then the owners are taught a different technique for quieting their barking dogs. A week later, the dogs and their owners return to the lab, the stimuli are introduced, and the duration of barking is measured. This is an example of what type of design? a. Posttest-only design with comparison group b. One-group pretest-posttest design c. Pretest and posttest design with comparison group d. Time series design with repeated reversal ANS: B

The one-group pretest-posttest, a pre-experimental design, named by Campbell and Stanley as the single-group pretest-posttest, is the most common design used for quasi-experimental nursing research. It exerts almost no control over the effects of extraneous variables, so interpretation of results is difficult. The posttest-only design with comparison group, known also as the posttest-only design with nonequivalent control group, is used in healthcare and occasionally nursing research. Campbell and Stanley called this design pre-experimental, with many threats to internal validity. In this design, an intervention is designed to produce values that are different from a certain range of values observed in similar populations. The values obtained for the intervention group are then compared with average values in a comparison group. The pretest-posttest design with nonrandom control group, also sometimes called the pretest-posttest design with comparison group, is used fairly often by healthcare researchers and social scientists. It has the same structure as the classic experimental design, except that its groups are not randomly assigned. In its simplest form, the time series with repeated reversal design, called the equivalent time samples design by Campbell and Stanley, involves subjects receiving an intervention followed by measurement. Then the intervention is removed, or it extinguishes, or the “usual treatment” is applied. Then dependent variables of the subjects are again measured. Then the treatment is applied again, and so forth, with treatment and removal of treatment continuing for two full cycles or more. It is useful for demonstrating the effect of a treatment, using subjects as their own controls. DIF:

Cognitive Level: Application

7. Identify the study design used in the following research project: Twenty patients, all of whom have bipolar mania, have been placed on lithium and also begun on a medication believed to prevent rapid cycling. The patients are followed for 12 months, at which time they are seen by a psychiatrist monthly, to adjust their dosages. Medication compliance, emergency department visits, and mental health hospitalizations are measured. These are compared with another group of patients with the same mental illness, being treated on lithium alone. What is this design? a. Posttest-only design with comparison group b. Pretest-posttest design with comparison group c. Pretest-posttest design with repeated reversal d. Solomon four-group design ANS: A

The posttest-only design with comparison group, known also as the posttest-only design with nonequivalent control group, is used in healthcare and occasionally nursing research. Campbell and Stanley called this design pre-experimental, with many threats to internal validity. In this design, an intervention is designed to produce values that are different from a certain range of values observed in similar populations. The values obtained for the intervention group are then compared with average values in a comparison group. The pretest-posttest design with nonrandom control group, also sometimes called the pretest-posttest design with comparison group, is used fairly often by healthcare researchers and social scientists. The design’s strengths are magnified when data are collected from the comparison group at the same time as from the experimental group, controlling for the history threat. The time series with repeated reversal design is just as successful as the time series design with comparison group in controlling for threats to internal validity, because subjects are measured repeatedly over time, and they act as their own controls. In this design, data usually are interpreted within subjects, analyzing whether the treatment was effective at a statistically significant level for each single subject. For this reason, the time series with repeated reversal design also is termed single subject research. The Solomon four-group design is an alternative to the posttest-only control group design and is used to control for the testing threat, not by eliminating testing from the design but by measuring the effect of testing on subsequent scores. Although this design is of some use in nursing education, it is used rarely in clinical settings because of most nurses’ unfamiliarity with the design and with the complexity of its implementation. The Solomon four-group design combines the groups of the classic experimental design and the posttest-only control group design. It consequently includes four groups, all randomly assigned, that receive pretest-treatment-posttest, pretest-no treatment-posttest, treatment-posttest only, and posttest only. The Solomon four-group design provides excellent control for the major threats to internal validity. As such, it is the polar opposite of the single group pretest-posttest quasi-experimental design, which has poor internal validity, throughout. DIF:

Cognitive Level: Application

8. A study’s hypothesis that a new surgical approach produces safer outcomes in immunosuppressed patients is tested in a 14-site research study across the United States. Subjects at all sites are randomly selected and randomly assigned to experimental versus control groups. What strategy is used in this research project? a. Quasi-experimental design b. Randomized-controlled trial c. Model testing design d. Counterbalancing ANS: B Randomized-controlled trials (RCTs) use the pretest-posttest control group design or one closely related to it. RCTs are conducted in order to produce definitive evidence for an intervention. Clinical trials may be carried out simultaneously in multiple geographical locations to increase sample size and resources and to obtain a more representative sample. In this case, the primary researcher must coordinate activities at all study sites. The possibility of carryover is measured by counterbalancing pieces of the intervention, so that the various steps of the treatment are administered in random order rather than being provided consistently in the same order. Model-testing designs use correlational research for measurement of proposed relationships within a theoretical model.

DIF:

Cognitive Level: Analysis

9. John Stuart Mill insisted that in order for causation to be demonstrated, there must be no alternative explanation for why a change in one variable leads to a change in the other variable. This concept of alternative explanations is the idea that underlies which type of validity? a. Construct validity b. Internal validity c. External validity d. Statistical conclusion validity ANS: B Construct validity refers to the congruence between the conceptual definition of a variable and the operational definition. In interventional research, internal validity is the degree to which changes in the dependent variable occur as a result of the action of the independent variable. External validity is the extent to which research results may be generalized back to the population. Statistical conclusion validity refers to correctness of the decisions the researcher makes regarding statistical tests used in the research. DIF:

Cognitive Level: Synthesis

10. The essentialists insisted that a cause be necessary and sufficient for an effect to occur. In a modern study, alcohol dependency is found to lead eventually to permanent liver damage, except when the person with alcoholism consumes a diet plentiful in the B- vitamins. In addition, liver damage can emerge in the absence of alcohol dependency. What would the essentialists say about the causative relationship between alcohol dependency and liver damage? a. The proposed cause is necessary, but not sufficient. b. The proposed cause is neither necessary nor sufficient. c. The proposed cause is sufficient, but not necessary. d. The proposed cause is both necessary and sufficient. ANS: B A philosophical group known as essentialists dates from the time of Plato and Aristotle. The essentialists proposed two adjectives for causality: necessary and sufficient. The proposed cause must be necessary for the effect to occur. (The effect cannot occur unless the cause first occurs.) The proposed cause must also be sufficient (requiring no other factors) for the effect to occur. This means that causation is not present if a cause seems to result in an effect only some of the time. In this example, alcohol dependency is not necessary for the development of liver damage: liver damage can result from other causes. In addition, alcohol dependency is not sufficient for the development of liver disease: if B-vitamin intake is adequate, liver disease may not occur. DIF:

Cognitive Level: Analysis

11. The researcher divides his lab rats into two groups and administers IV methamphetamine to one of the groups, in order to determine its effect on the fear-flight response. This is an example of which of the following? a. Bias

b. Manipulation c. Correlation d. Multiple causality ANS: B Manipulation is one of the hallmarks of experimental research, and it is absent from non-interventional research. Manipulation in interventional research means that the researcher enacts an intervention that alters the value of the independent variable, then measures the resultant effect on one or more dependent variables. The most common values for the independent variable are “present” and “absent”: present for the experimental group and absent for the control group. Manipulation in an experiment must be due to the researcher’s action. The word bias is derived from a French word that means slant or oblique. In common parlance, it refers to a point of view that differs from truth—it slants away from the square, the objective, the balanced, leaning to one side. Correlational research is conducted in order to establish the direction and the strength of relationships between or among variables, as they exist in a natural setting. Multiple causality refers to the case in which two or more variables combine in causing an effect. DIF:

Cognitive Level: Application

12. A researcher is comparing a new and less expensive treatment with an established treatment, in hopes of showing that there is no difference in outcome. The researcher does not perform a power analysis and, consequently, selects a sample size that is smaller than what would be recommended for an analysis of variance. The results show that there is no significant difference in outcome between the two treatments. Which type of validity is affected by this? a. Construct validity b. Internal validity c. External validity d. Statistical conclusion validity ANS: D Construct validity refers to the congruence between the conceptual definition of a variable and the operational definition. In interventional research, internal validity is the degree to which changes in the dependent variable occur as a result of the action of the independent variable. External validity is the extent to which research results may be generalized back to the population. Statistical conclusion validity refers to correctness of the decisions the researcher makes regarding statistical tests used in the research. DIF:

Cognitive Level: Analysis

13. A researcher is comparing a new and less expensive treatment with an established treatment, in hopes of showing that there is no difference in outcome. The researcher does not perform a power analysis and, consequently, selects a sample size that is smaller than what would be recommended for an analysis of variance. The results show that there is a significant difference in outcome between the two treatments, and that the new treatment has poorer outcomes. What is the negative result of the researcher’s decision to use a smaller sample? a. The statistical conclusions reached are incorrect. b. There is no negative result. c. The study will have to be replicated, because its sample was small.

d. The researcher is guilty of misconduct. ANS: B Statistical conclusion validity is concerned with whether the conclusions about relationships or differences drawn from statistical analysis are an accurate reflection of the real world: did the researcher use the right statistical tests in the proper way? The test was used in the proper way, and the results established a difference in outcomes between the established treatment and the new one, meaning that the difference in outcomes must have been quite pronounced for this to be evident with a small sample. (The effect size is large.) The results dramatically underscore this. DIF:

Cognitive Level: Analysis

14. A researcher tests a new intervention for nausea associated with chemotherapy, in hospitalized patients. At the same time, a new over-the-counter medication containing natural herbs is marketed aggressively, and some of the hospital patients are given this herbal remedy by their families. This is a threat to which type of validity? a. Construct validity b. Internal validity c. External validity d. Statistical conclusion validity ANS: A Construct validity refers to the congruence between the conceptual definition of a variable and the operational definition. In this instance, the researcher failed to define the control condition, so that it specifically excluded subjects from self-administering herbal supplements to control nausea. In interventional research, internal validity is the degree to which changes in the dependent variable occur as a result of the action of the independent variable. External validity is the extent to which research results may be generalized back to the population. Statistical conclusion validity refers to correctness of the decisions the researcher makes regarding statistical tests used in the research. DIF:

Cognitive Level: Analysis

15. A researcher tests a new intervention for nausea associated with chemotherapy in hospitalized patients. The researcher does not want to suggest nausea to the patients, so as the dependent variable, the researcher uses the answer the patients give to the question, “How are you feeling this morning?” This is a threat to which type of validity? a. Construct validity b. Internal validity c. External validity d. Statistical conclusion validity ANS: A Construct validity refers to the congruence between the conceptual definition of a variable and the operational definition. In interventional research, internal validity is the degree to which changes in the dependent variable occur as a result of the action of the independent variable. External validity is the extent to which research results may be generalized back to the population. Statistical conclusion validity refers to correctness of the decisions the researcher makes regarding statistical tests used in the research.

DIF:

Cognitive Level: Analysis

16. A researcher conducts interventional research and uses a small sample that is not randomly selected. When the researcher replicates the study, twice, the researcher again uses the same site and another small sample that is not randomly selected. This is a threat to which type of validity? a. Construct validity b. Internal validity c. External validity d. Statistical conclusion validity ANS: C Construct validity refers to the congruence between the conceptual definition of a variable and the operational definition. In interventional research, internal validity is the degree to which changes in the dependent variable occur as a result of the action of the independent variable. External validity is the extent to which research results may be generalized back to the population. Statistical conclusion validity refers to correctness of the decisions the researcher makes regarding statistical tests used in the research. DIF:

Cognitive Level: Analysis

17. What is the essential difference between a control group and a comparison group? a. A control group is used in interventional research. A comparison group is used in non-interventional research. b. A control group is larger in size than a comparison group. c. A control group exists only in a basic lab situation. All nursing studies use comparison groups. d. A control group controls for the effects of potential extraneous variables. A comparison group does not. ANS: D Control groups in experimental research control for the effects of potential extraneous variables. The traditional control group is randomly assigned in this type of research. If a change occurs in the dependent variable in the treatment (experimental) group and not in the randomly assigned control group, the researcher can be fairly confident that the independent variable caused the change in the dependent variable, and that the change was not merely the result of an uncontrolled-for extraneous variable. The presence of a randomly assigned control group is a requirement of experimental designs. Quasi-experimental research can be said to use a control group when the researcher is able to obtain a group that is very similar to the experimental group. That control group might be obtained by random assignment, by matching, or by using subjects as their own controls. The reason these are considered control groups is that they control, at least to some extent, for the effects of extraneous variables. They do the job a control group should do. Comparison groups are groups created for the purpose of comparison, and they are not products of random assignment. When a researcher identifies one of the groups in a study as a control group, but it does not control for any extraneous variables, the group is by default a comparison group. This is the case in which research data are compared with national norms or averages, or with standard universal values, such as serum sodium levels. These norms or averages are included for purposes of comparison, not control.

DIF:

Cognitive Level: Application

18. A researcher uses matching to constitute a control group, while performing a study on psychotherapy as an adjunct treatment for substance addiction. What type of validity might be enhanced by matching, in this instance? a. Construct validity b. Internal validity c. External validity d. Statistical conclusion validity ANS: B Sometimes it is possible to match experimental group subjects individually with controls, either drawn from a database that spans a recent time period, or occasionally selected from individuals not receiving the experimental treatment at the same time data are collected for the experimental group. A group selected by matching can control, to some extent, for extraneous variables. In interventional research, internal validity is the degree to which changes in the dependent variable occur as a result of the action of the independent variable, and it reflects design-embedded decisions that control for the effects of extraneous variables. Construct validity refers to the congruence between the conceptual definition of a variable and the operational definition. External validity is the extent to which research results may be generalized back to the population. Statistical conclusion validity refers to correctness of the decisions the researcher makes regarding statistical tests used in the research. DIF:

Cognitive Level: Synthesis

19. Immediately after the intervention in an experimental study of the negative effects of smoking tobacco, the state tax on cigarettes increases the cost from $4 to $8 per pack. Which threat to internal validity does this pose? a. Mortality b. History c. Testing d. Selection ANS: B The history threat, often simply called history, is the occurrence of an event external to the research that affects the dependent variable. In an interventional study, the researcher controls for the history threat by using a design that provides for a separate control group and concurrent data collection in both groups. DIF:

Cognitive Level: Application

20. Subjects in a multiple group experimental study are tested for how much time it takes them to navigate a maze and find the chocolate. The maze is reconstructed after each run, and three different floor plans are used. Each group is tested eight times in 8 hours at a different time of day. The runs later in the day have faster times than the earlier ones. Which threat to internal validity might account for this difference? a. Instrumentation b. Selection c. Testing

d. Statistical regression toward the mean ANS: C The testing threat refers to the effect of taking a pretest upon subsequent posttest scores. If the same test serves as both pretest and posttest, subjects may purposefully learn the answers in the interval between testing sessions. If a different test is used, subjects may still do better on the posttest because they know what material is likely to be tested. In this scenario, each maze run can be interpreted as a test; the subjects remember the maze patterns they’ve already encountered, as the day progresses. The instrumentation threat refers to changes in the instrument used, or its calibration, that occur during the course of the experiment. In interventional research, the selection threat is introduced when subject assignment to group occurs in a nonrandom way. The threat of statistical regression toward the mean is present when subjects are selected for study participation because they display extreme scores of a screening variable. DIF:

Cognitive Level: Application

21. A researcher believes that therapy is more effective if patients exercise. The researcher tells the patients that it has been arranged for them to use the hospital gym, if they so desire—and that if they are interested, they will then be in the experimental group. This represents which threat to internal validity? a. Maturation b. Attrition c. History d. Selection ANS: D In interventional research, the selection threat is introduced when subject assignment to group occurs in a nonrandom way. The history threat, often simply called history, is the occurrence of an event external to the research that affects the dependent variable. Maturation refers to normal changes like fatigue, hunger, growth, development, and aging that occur as a function of time, not because of the action of the independent variable. These normal changes may affect the value of the dependent variable. Attrition refers to subjects dropping out of the study after it is already in progress. DIF:

Cognitive Level: Application

22. What is the strategy used to determine whether the carryover effect exists? a. Random assignment b. Counterbalancing c. Sequencing d. Bias control ANS: B

Sometimes the application of one treatment can influence the response to later treatments, a phenomenon referred to as a carryover effect. The carryover effect may also be called the order effect, labeled as such because the order of the interventions may influence the dependent variable. If a carryover effect is known to occur, the researcher may be able to minimize its effect by allowing for washout or using a counterbalanced design. Counterbalancing means administering the various treatments in random order rather than providing them in the same sequence. DIF:

Cognitive Level: Comprehension

23. A researcher tests the effect of a new laparoscopic treatment for chronic shoulder dislocation, comparing it with an older treatment. The results are statistically significant, and the researcher states in the study findings that there is evidence that the treatment has promise for widespread application. A subsequent replication study fails to show statistical significance. A third and fourth study produce the same effects as the second. Sample sizes are determined to be sufficient in all four studies. What is the most likely explanation here? a. A Type I error occurred in the first study. b. A Type II error occurred in the second, third, and fourth studies. c. External validity is excellent. d. Operationalization of variables was faulty. ANS: A If the findings generated in an approximate replication are not consistent with an original study, there are three possibilities: a Type I error (rejecting the null hypothesis in error) occurred in one or the other study, a Type II error (accepting the null hypothesis in error) occurred in one of the studies, or the changes in research methods such as setting and sample characteristics are responsible for the different findings. However, the reasons for the inconsistent results may not be immediately apparent. In the case of a Type I error, still another replication should be conducted. In the case of a possible Type II error, a post hoc power analysis should be conducted to determine whether the sample was too small, because that is the most common reason a Type II error occurs. If so, another replication with a larger sample should be conducted. In the third case, the methods that changed, such as constitution of the sample or nature of the setting, should be scrutinized to determine the reasons the results changed. Common sense dictates another replication in any of the three cases: more information is needed. Construct validity refers to the congruence between the conceptual definition of a variable and the operational definition. This does not affect statistical calculations. External validity refers to the ability to generalize findings to members of the population: it is obviously not excellent if the results should not be generalized. DIF:

Cognitive Level: Analysis

24. A researcher conducts a study examining the relationship between exercising at a gym and quality of life in elders over 70 years of age. There appears to be no statistically significant relationship. Then the researcher analyzes the data again, this time comparing number of times a week the participant goes to the gym and quality of life and finds that there is a statistically significant relationship. This is an example of which of the following? a. Statistical conclusion validity b. Control

c. Partitioning d. Causality ANS: C Partitioning means dividing a variable into subsets for analysis. The variable being divided may be the independent variable under the control of the researcher or it may be a potentially confounding variable. If the independent variable (the treatment) is partitioned, the researcher may randomly assign participants to the control group and to multiple treatment groups, each of which will receive varying amounts or doses of the independent variable. DIF:

Cognitive Level: Application

MULTIPLE RESPONSE 1. Patients in an outpatient treatment center receiving daily wound care were studied by means of an experimental design using a crossover strategy. Patients were administered either Morphine Contin or Percocet, by random assignment, on one day, and the other medication on the following day. Pain scores were obtained for both days, recorded and analyzed. Why was a crossover strategy used? (Select all that apply.) a. Because wound care may become less painful in some patients over time, as wounds heal, this strategy balanced the pain scores, across participants. b. Because wound care may become more painful over time, as debridement occurs, exposing raw tissue, this strategy balanced the pain scores, across participants. c. Because patients were not consented for the study and had to receive at least one traditional treatment. d. Because wound care may become less painful over time, as patients know what to expect, this strategy compensated by alternating first-treatment across patients. ANS: A, B, D The crossover design, or the counterbalanced design, is the classic experimental design with at least one additional period of data collection, in which experimental and control conditions are reversed. In this design, all subjects receive the intervention once and the control condition once. The design controls for threats to internal validity as well as a traditional experimental design does, because of its random assignment of subjects to group. Wound healing is a complex phenomenon, unique to each person. Wound care may become more or less painful, as a wound heals. DIF:

Cognitive Level: Analysis

2. What are the differences between the simple quasi-experimental pretest-posttest design and an experimental version of the same design with a control group, in which there is random assignment to group? (Select all that apply.) a. This experimental design controls for the effects of more extraneous variables than does the quasi-experimental one. b. Subjects are blind to group assignment in the experimental design but not in the quasi-experimental design. c. In the experimental version, there is better construct validity. d. This experimental design controls for the history threat to internal validity,

whereas the quasi-experimental one does not. e. This experimental design controls for the testing threat to internal validity, whereas the quasi-experimental one does not. ANS: A, C, D In the one-group pretest-posttest design, measurement is obtained for a single group, followed by an intervention and a second measurement of the dependent variable. The design exerts very poor control over the effects of extraneous variables, so interpretation of results is difficult. In the pretest-posttest control group design, the researcher randomly assigns consented subjects to either treatment or control group and measures the dependent variable or variables in both groups. Then the researcher applies the intervention to the treatment group only and, after the intervention is complete, measures the dependent variable(s) again in both groups. The name for the design is the pretest-posttest control group design because there is both a pretest and a posttest of the dependent variable(s) in the experimental group, and there is a control group that is concurrently pretested and posttested. When this design is used, control for effects of extraneous variables is very good, although it does not control for the testing threat. When the history threat to internal validity exists, an event external to the research occurs and affects the dependent variable. The testing threat refers to the effect of taking a pretest upon subsequent posttest scores. Construct validity is related to operational definitions of variables, not to type of design. Blinding or masking is the strategy of not revealing to subjects whether they are experimental or control subjects. Some experimental studies use blinding and some do not. The original, or classic, experimental design, called the pretest-posttest control group design, is still the most commonly used experimental design. There are two randomized groups, one receiving the experimental treatment and one receiving no treatment, a placebo treatment, or the routine or standard care. By comparing pretest scores and the groups’ demographic characteristics, one can evaluate the effectiveness of random assignment in providing equivalent groups. The researcher implements the treatment or independent variable under very controlled conditions. The dependent variable is measured twice, before and after the manipulation of the independent variable. DIF:

Cognitive Level: Synthesis

3. A posttest-only design with a comparison group, which is a quasi-experimental study, lacks conditions present in an experimental study. Which components are lacking in this type of study design? (Select all that apply.) a. A control group b. An intervention c. Random assignment to group d. A pretest e. A comparison group ANS: A, C, D The posttest-only design with comparison group is used in healthcare and occasionally nursing research. Campbell and Stanley called this design pre-experimental, with many threats to internal validity. In this design, an intervention is designed to produce values that are different than a certain range of values observed in similar populations. The values obtained for the intervention group are then compared with average values in a comparison group. Generalization is possible but it is limited, because of the design’s threats to validity.

DIF:

Cognitive Level: Evaluation

4. A nurse notes that in clients with multiple tattoos, many are missing quite a few of their teeth. The nurse measures the variables and establishes a negative correlation between number of tattoos and number of teeth. The nurse designs a study to measure causation. Why is this problematic? (Select all that apply.) a. Tattooing can be expensive. b. Causing subjects to become multiply tattooed, so as to cause their teeth to fall out, is ethically questionable. c. Random assignment to group would be impossible. d. The nurse researcher cannot cause subjects’ teeth to fall out, so as to later measure if their number of tattoos has increased; that would be ethically questionable. e. The study would have to be designed as a large-sample, multisite design. ANS: B, D Interventional research examines causality, in either a quasi-experimental or an experimental design. Based on the correlational findings, it is not clear which variable causes the other to occur. The principle of beneficence requires the researcher to do good and “above all, do no harm.” DIF:

Cognitive Level: Evaluation

5. In a national health study, begun in 2012, thousands of nurses have been participating in ongoing research to better understand the effects of omega-3 fish oil and vitamin D-3 upon cardiovascular health and bone health. Subjects are randomly assigned to experimental or control group, for the two variables. Data about cardiovascular health and bone health will continue to be collected over many years. This study could be an example of what types of research? (Select all that apply.) a. Prospective b. Retrospective c. Factorial study d. Crossover design e. Descriptive f. Correlational g. Experimental h. Quasi-experimental ANS: A, C, G

Retrospective means looking backward, usually in relationship to time. A retrospective study uses preexistent data collected for other purposes. This study uses data collected by the researchers for the purpose of this study and is, consequently, prospective. Quantitative research may be interventional or non-interventional. Interventional designs test the effect of a researcher’s actions, called interventions, on a measured result. Interventional research includes both experimental and quasi-experimental designs. non-interventional designs count and measure characteristics about the phenomenon of interest and the study’s variables, as they exist naturally, without researcher intervention. They include both descriptive and correlational research. A factorial design tests for multiple causality using two or more independent variables. For a “2  2” study with two independent variables, subjects are randomly assigned to one of four groups: A receives both variables, B receives one variable, C receives the other variable, and D is the control group and receives neither variable. In the crossover design, the subject is randomly assigned to treatment or control condition for the first data-collection period; then for the second, each subject is placed into the opposite group. DIF:

Cognitive Level: Synthesis

6. A researcher is designing a randomized-controlled trial (RCT). What must an RCT contain? (Select all that apply.) a. Random collection of data in both groups b. Random operationalization of the dependent variable c. Random assignment to group d. An interventional design e. Random application of the independent variable ANS: C, D Randomized-controlled trials (RCTs) use the pretest-posttest control group design, or one closely related to it. They are conducted in order to produce definitive evidence for an intervention. Clinical trials may be carried out simultaneously in multiple geographical locations to increase sample size and resources and to obtain a more representative sample. DIF:

Cognitive Level: Analysis

7. Which research methods test for causality? (Select all that apply.) a. Experimental research b. Causational modeling c. Case study research d. Quasi-experimental research e. Cross-sectional research ANS: A, D

Quasi-experimental and experimental designs examine causality. The power of the design to accomplish this purpose depends on the degree to which the actual effects of the experimental treatment (the independent variable) can be detected by measuring the dependent or outcome variable. Correlational studies examine relationships between variables, but do not provide information on causality. The case study design involves an intensive exploration of a single unit of study, such as a person, family, group, community, or institution, or a small number of subjects who are examined intensively, and it is considered a qualitative strategy. Cross-sectional designs are correlational designs that examine change over time. DIF:

Cognitive Level: Analysis

8. A researcher states in an article, “The subjects acted as their own controls.” If this is true, what does this imply? (Select all that apply.) a. Statistical significance was most likely calculated for each subject individually. b. There were so few subjects that a separate control group could not be obtained. c. Measurement of the subjects was made at least twice. d. Two studies were performed. e. The methodology was quasi-experimental. f. The study was interventional. ANS: A, C, E, F In a quasi-experimental design, the time series with repeated reversal involves subjects receiving an intervention followed by measurement. Then the intervention is removed, or it extinguishes, or the “usual treatment” is applied. Then dependent variables of the subjects are again measured. Then the treatment is applied again, and so forth, with treatment and removal of treatment continuing for two full cycles or more. It is useful for demonstrating the effect of a treatment, using subjects as their own controls. The design is just as successful as the time series design with comparison group in controlling for threats to internal validity, because subjects are measured repeatedly over time, and they act as their own controls. In this design, data usually are interpreted within subjects, analyzing whether the treatment was effective at a statistically significant level for each single subject. For this reason, the time series with repeated reversal design also is termed single subject research. For obvious reasons, the researcher seeks a sample that is somewhat representative of the population but, more important, inclusive of major groups, in terms of age, gender, race, and other demographics pertinent to the research. Generalization is limited, certainly, but the argument for use of the intervention in similar subjects is more compelling when based on a broad representation of many demographic factors. This design is very desirable for small populations and limited access to subjects. DIF:

Cognitive Level: Evaluation

9. Threats to statistical conclusion validity include which of the following? (Select all that apply.) a. Fishing b. Low statistical power c. Maturation d. Violated assumptions of statistical tests e. History

ANS: A, B, D Statistical conclusion validity refers to correctness of the decisions the researcher makes regarding statistical tests used in the research. The principal ones to consider are low statistical power, violated assumptions of statistical tests, and fishing. Maturation and history are threats to internal validity. Each statistical test has “rules” for the cases in which it can be used—the researcher must be careful not to violate these rules, or assumptions. Low statistical power is present when a study sample is not large enough to result in statistically significant findings. Especially when the effect size of an intervention is small, a substantial sample may be required to generate power sufficient to demonstrate significance. Fishing for statistical significance by performing multiple statistical tests results in an additive error rate. Sooner or later, Type I error will occur. The maturation threat refers to normal changes like fatigue, hunger, growth, development, and aging that occur as a function of time, not because of the action of the independent variable. These normal changes may affect the value of the dependent variable. The history threat refers to an event external to the research that occurs, affecting the dependent variable. DIF:

Cognitive Level: Comprehension

10. Causality is tested through which of the following? (Select all that apply.) a. Grounded theory research b. Experimental research c. All quantitative research d. Historical research e. Quasi-experimental research ANS: B, E Experimental designs are the most definitive way to establish evidence of causation. Quasi-experimental designs are used when a researcher decides that an experimental design cannot or should not be used for an interventional study but it is the only option available to test the effect of the intervention. DIF:

Cognitive Level: Comprehension

11. In which of the following ways does the researcher control for threats to construct validity? (Select all that apply.) a. Random selection b. Use of double-blinding c. Random assignment to group d. Measuring dependent variables with more than one strategy e. Thoughtful crafting of conceptual definitions ANS: B, D, E Measuring the dependent variable with more than one strategy prevents mono-operational bias, a threat to construct validity. Thoughtful crafting of conceptual definitions prevents inadequate preoperational clarification of constructs and prevents confounding constructs, both threats to construct validity. Use of double-blinding prevents both subjects and research team from knowing subjects’ group membership, so that the Rosenthal effect does not occur (the belief of the person collecting the data that might encourage responses from subjects that either support those beliefs or oppose them).

DIF:

Cognitive Level: Analysis

12. In interventional research, why does subject attrition affect internal validity? (Select all that apply.) a. A study in which the majority of the subjects die calls into question whether the treatment itself is safe. b. Subjects who drop out may differ from those who stay in the study, in terms of an important extraneous variable. c. If subjects drop out of the control group, and not the experimental group, it strongly implies that there is some benefit to participation of which the researchers may not be aware. d. Subject mortality may result in a sample that is so much smaller than anticipated that Type II error may result. e. Type I error is almost guaranteed with very unequal sample sizes. ANS: B, C The threat of attrition refers to research subjects dropping out of a study that is already in progress. This can make experimental and control groups dissimilar. The reason for this is that when attrition is proportionately higher in one group than the other, randomly assigned groups become less alike. The difference in the value of the dependent variable may be due to the researcher’s intervention, or to dissimilarity between the evolved groups. Statistical testing is based on probabilities, not certainties. In nursing research, the level of significance typically is set at p < 0.05 for the hypothesis testing process. This means that the researcher will allow for a 5% or lower probability of rejecting the null hypothesis when it is indeed true. When this happens it is called a Type I error. The probability of accepting the null hypothesis when it is false is called a Type II error. In nursing research, the researcher usually allows a 20% or lower probability of the occurrence of a Type II error. DIF:

Cognitive Level: Synthesis

13. Aside from random assignment using a large sample, what are design strategies that control for known extraneous variables? (Select all that apply.) a. Matching b. Selection of a heterogeneous sample c. Selecting a homogeneous sample d. Use of stratified random sampling e. Setting inclusive sampling criteria ANS: A, C Sometimes a researcher identifies a potentially extraneous variable that exists in an identifiable portion of the population and, for that reason, decides to narrow the study’s inclusion criteria in order to exclude that subpopulation, making the sample more homogeneous. A homogeneous sample contains subjects who are alike, sharing one or more characteristics; a heterogeneous sample contains subjects who are mixed, in terms of characteristics. Homogeneous samples allow generalization to a similar homogeneous population; heterogeneous samples allow broader generalization. Quasi-experimental research can be said to use a control group when the researcher is able to obtain a group that is very similar to the experimental group. DIF:

Cognitive Level: Analysis

14. What is the most effective way to minimize the effect of a large number of unknown extraneous variables? (Select all that apply.) a. Match the groups by hand. b. Randomly assign subjects to treatment and control group. c. Use an experimental design. d. Place subjects into groups according to the extraneous variables they possess. e. Allow subjects to choose the groups to which they want to belong. f. Use a large sample. ANS: B, C, F The ability of random assignment with a large sample to control for the effects of extraneous variables is a powerful tool in research. The truth of the strategy is that random assignment of subjects to treatment and control groups controls for the effects of most extraneous variables quite well, if the sample is large. Control groups in experimental research control for the effects of potential extraneous variables. The traditional control group is randomly assigned in this type of research. If a change occurs in the dependent variable in the treatment (experimental) group and not in the randomly assigned control group, the researcher can be fairly confident that the independent variable caused the change in the dependent variable, and that the change was not merely the result of an uncontrolled-for extraneous variable. DIF:

Cognitive Level: Application

15. What designs can a researcher use, so as to control for the testing threat? (Select all that apply.) a. Solomon four-group design b. Any design that uses a nested strategy c. Any experimental design d. Posttest-only control group design e. One-group pretest-posttest ANS: A, D Selecting the Solomon four-group design controls for the testing threat to internal validity. The posttest-only control group design also controls for the testing threat: if pretesting would change subjects’ perceptions, it makes sense to not pretest, provided that subjects are randomly assigned to group before the treatment. Not all experimental designs control for the testing threat: taking a pretest affects subsequent test scores. The one-group pretest-posttest design introduces the testing threat, as well. DIF:

Cognitive Level: Application

16. Why does a researcher perform a post hoc analysis comparing characteristics in experimental group and control group? (Select all that apply.) a. To eliminate the effect of confounding variables b. To measure the effect of testing on subsequent scores c. To determine whether the characteristics were similar in both groups d. To measure the effect of an extraneous variable by statistical analysis e. To make a logical argument that the characteristics that are similar between groups did not affect the value of the dependent variable

ANS: C, E Researchers often compare the experimental group characteristics and control group characteristics and provide a table of these in the research report, with the percentage distribution in each per group, for confirmation of their sameness. An example would be an examination of the proportion of men versus women in both groups. This is called “post hoc” analysis, from the Latin “after this one.” In table 1, the demographic variables and other known extraneous variables, such as age and medical diagnoses, are described along with the results of the post hoc analyses. The researcher may measure other extraneous variables as well, such as medical diagnoses or number of people in the household, on the suspicion that they too might intrude significantly upon the results. These are displayed either with the demographics or in a different table. A confounding variable is a special subtype of extraneous variable, but it is unique in that it is embedded in the study design because it is intertwined with the independent variable. Confounding variables must be eliminated before a study is conducted, during operational definition of variables. The Solomon four-group design is an alternative to the posttest-only control group design and is used to control for the testing threat, not by eliminating testing from the design but by measuring the effect of testing on subsequent scores. Random sampling increases the probability that subjects with various levels of an extraneous variable are included and are randomly dispersed throughout the groups within the study. This strategy is particularly important for controlling unidentified extraneous variables. DIF:

Cognitive Level: Application

Chapter 12: Qualitative Research Methods Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. In addition to the aim or goal of the study, the purpose statement for a qualitative study should

include the population, and often the setting. What else should be included in the qualitative purpose statement? a. The phenomenon of interest b. The justification for conducting the study c. The theoretical framework used d. The hypothesis ANS: A

Purposes should clearly identify the goal or aim of the study that has emerged from the research problem and literature review. The purposes of qualitative studies include the phenomenon of interest, the population, and often the setting. Study purposes such as testing an intervention and measuring the effectiveness of a program, which would involve a hypothesis, are not consistent with qualitative approaches. Most qualitative researchers do not identify specific theoretical frameworks during the design of their studies, as is expected for quantitative studies. As in quantitative research, if a rationale for conducting the study is included by the authors, it appears in the problem statement. The problem statement also includes a second essential component, a justification for the importance of addressing this knowledge gap, be it social, psychological, physiological, cognitive, financial, humanistic, or philosophical. This is sometimes called the significance statement. DIF: Cognitive Level: Comprehension 2. Quantitative research study subjects are selected so that they are as representative of a

population as possible. What is the principal reason behind the selection of qualitative study participants? a. The participants are philosophically attuned to the use of narratives and narrative analysis as the best means to convey their experience to the researcher and to others. b. The participants meet the requirements for involvement in the study that the researcher specified at the outset of the study’s implementation. c. The participants are as representative of the population as possible. d. The participants have experienced the phenomenon of interest. ANS: D

Qualitative researchers seek participants who have experience the phenomenon of interest, are willing to participate, and are able to share their experiences or perspectives. In qualitative research, no generalizations are made. Participants’ philosophical attunement to narratives and narrative analysis is not required. In some types of published research involving convenience sampling, for instance Internet studies and group observations in public places, the researcher cannot verify whether participants meet the inclusion criteria for the study. DIF: Cognitive Level: Analysis 3. Which statement related to sample size is true of qualitative methodologies?

a. An adequate sample size for qualitative research is between 25 and 50 participants. b. Samples used in qualitative research are typically much larger than in quantitative

research. c. The size of the qualitative sample to be used is decided upon in the design phase of

a study. d. The criterion of data saturation, or theoretical sufficiency, is used to determine the

point at which the sample size is adequate. ANS: D

The actual number of participants in a qualitative study depends on when data saturation is achieved. Data saturation is the point at which new data begins to be redundant with what has already been found, and no new themes can be identified. This point is also referred to as theoretical sufficiency. Samples for qualitative research studies are notably smaller than samples used in quantitative studies. Data saturation, or gathering data to the point where one is no longer learning new information about the phenomenon, is a term used to determine when the sample size is adequate. The sample for a rigorous qualitative study is not as large as the sample for a rigorous quantitative study. When applying for human subjects’ approval, the researcher will be asked the maximum sample size. Giving a generous range of 12 to 25 participants can be a way to answer this question but will depend on the study design. DIF: Cognitive Level: Analysis 4. What is the term that signifies the qualitative researcher’s awareness of personal biases and

past experiences that might influence the researcher’s interpretation of participants’ responses or other data, allowing accurate and honest assessment? a. An etic view b. Reflexivity c. Bracketing d. An emic view ANS: B

The awareness and ability to be involved with the participants and yet be able to analyze the data abstractly with intellectual honesty is called reflexivity. Reflexivity consists of the ability to be aware of one’s biases and past experiences that might influence how one would respond to a participant or interpret the data. Researchers subscribing to the phenomenologist Husserl’s views would use bracketing, which is consciously identifying, documenting, and choosing to set aside one’s own views on the phenomenon. The emic view represents the perspective of the research participants and, presumably, other insiders in a culture. The etic view reflects the outsider’s view of the culture: how the culture appears to the outside world. DIF: Cognitive Level: Comprehension 5. Probing is a strategy used in interviews to: a. Make it clear that the interviewer is in charge. b. Limit the range of responses. c. Elicit more information in a specific area. d. Ensure a variety of interpretations of the question by different subjects. ANS: C

Encouraging a research participant to elaborate further on a particular dimension of the topic is called probing. It is a technique used to elicit more information. Probing involves the use of nonthreatening but thought-provoking questions. DIF: Cognitive Level: Comprehension 6. A clinical nurse at a large urban hospital decides to conduct a descriptive qualitative study

related to staff nurses’ perceptions of the causes of various types of violence against nurses in that facility. As part of the research design, the nurse hosts a series of focus groups with staff nurses during each of three shifts. What is considered the main advantage of using a focus group strategy as opposed to one-on-one interviews for data collection? a. People from differing social and cultural backgrounds tend not to share information as well as those who have common experiences. b. Focus groups allow full expression of individual voices and contrasting viewpoints, controlling bias. c. Focus groups can be spontaneous, and they require little advance planning or forethought. d. A focus group makes it possible to obtain the prevailing opinion of a small cluster of people in a fairly short period of time, as opposed to the strategy of one-to-one interviewing. ANS: D

Focus groups began as tools for market researchers. A focus group has been defined as a “semi-structured group interview designed to elicit information from participants on a defined topic of interest.” Focus groups, as a means of data collection, serve a variety of purposes in nursing research. These groups have been used to understand the experiences of people who are receiving care or may need care. Researchers have conducted focus groups to study mothering in women with ovarian cancer, quality of life with trauma patients, self-care management of older persons with heart failure, and communication about hypothermia with parents of neonates in intensive care. Collecting data with focus groups is a flexible and efficient method. DIF: Cognitive Level: Application 7. What is the typical size and duration of a focus group interview? a. 4 to 12 participants; 3 1/2 hours b. 3 participants; 30 minutes c. At least 12 participants; 3 hours d. 4 to 12 participants; 45 minutes to 2 hours ANS: D

Focus groups typically last from 45 minutes to 2 hours. A 2-hour focus group usually has about 10 questions. Each focus group should consist of 4 to 12 participants. If there are fewer participants, the discussion tends to be inadequate. DIF: Cognitive Level: Knowledge 8. If a researcher decides to transcribe a recorded one-hour interview or focus group in order to

better understand the data and the views expressed by the participants, the researcher might need to spend up to how much time creating a verbatim transcript? a. 2 hours

b. 5 hours c. 6 hours d. 8 hours ANS: D

Transcription may require 3 to 8 hours for each 1 hour of interview or focus group time, depending on the equipment used and the transcriber’s skill. DIF: Cognitive Level: Application 9. A researcher is interested in studying the experiences of gay (G), lesbian (L), and transgender

(T) youth in the middle school setting. With parental consent and the students’ assent to participate, the researcher provided a group of 12 students with disposable digital cameras and had them each take 15 photos that illustrated their experiences, both positive and negative, as a GLT adolescent. The researcher then developed the photos and asked participants to discuss what they documented. This is an example of what type of qualitative data collection technique? a. Thick description b. Photovoice or photo novella c. Participatory research d. Data immersion ANS: B

Photovoice is the idea of participants using photographs to describe aspects of their communities and their lives, “recording and reflecting on the strengths and concerns,” and is most often used in participatory research studies. Caroline Wang and her colleagues are credited with guiding the first health-related study during which rural Chinese women were given cameras to photograph their lives and especially their health needs. Wang called this practice photo novella, but others since have used the term photovoice. Nurse researchers have used photovoice to gain insights into different cultures, even within the United States. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. Which of the following are true statements about the qualitative research methodology?

(Select all that apply.) a. Inductive reasoning is used in the data analysis process. b. Qualitative analyses involve using words rather than numbers as the basis of analysis. c. The researcher who is more sensitive to the participant’s feelings is able, through empathy, to make the participant feel valued and to establish rapport. d. The CAQDAS computer program converts qualitative data to quantitative data, preparatory to statistical analysis. e. As opposed to the case of quantitative research, qualitative researchers are able to modify sampling and data gathering processes once the study begins. f. Part of using oneself as a data-collection instrument is being cognizant that it is not about the researcher: the focus is on the participant’s perceptions and experiences. ANS: A, B, C, E, F

Qualitative analysis techniques use words rather than numbers as the basis of analysis. In qualitative analysis, reasoning flows from the images, documents, or words provided by the participant toward more abstract concepts and themes. This reasoning process, inductive thinking, guides the organizing, reducing, and clustering of the data. To achieve the goal of describing and understanding participant perspectives, qualitative methods of sampling, data gathering, and analysis allow for more flexibility than the methods of the quantitative paradigm. Because data analysis in most qualitative designs begins as data are gathered, insights from early data may suggest additional questions that need to be asked or other modifications to the study methods. The researcher’s personality is a key factor in qualitative research, in which skills in empathy and intuition are cultivated. The researcher needs to become closely involved in the subject’s experience to interpret it. Participants need to feel safe and able to trust the researcher prior to sharing their deepest experiences with the researcher. It is necessary for the researcher to be open to the perceptions of the participants rather than attaching the researcher’s own meaning to the experience. CAQDAS allows researchers to make notes about tentative themes and record decisions made during the analysis. An interview, although interactive, is not a social conversation. The focus is not on the researcher. Rather the focus is on the participant and the participant’s experience. DIF: Cognitive Level: Synthesis 2. Which of the following are true statements regarding data analysis in qualitative research?

(Select all that apply.) a. Qualitative data analysis involves examining and interpreting data in order to elicit meaning, gain understanding, and develop knowledge. b. Although qualitative data analysis may identify additional data that may need to be collected, once the data collection period is over, the researcher is discouraged from contacting participants again to gather additional information. c. Data analysis in some types of qualitative research occurs concurrently with data collection. d. Researchers “dwell with the data” by immersing themselves in transcripts, tapes, and interview notes, and then reflecting, to make sense not only of what participants have said but also of meanings underlying expressions, emphasis, and nonverbal communications. e. In all qualitative methods, data are analyzed according to the theoretical connections of the study framework. f. Qualitative researchers may defer the literature review until after data analysis is complete, to avoid bias. g. Hypotheses guide qualitative data analysis. ANS: A, C, D, F

Data analysis in most qualitative designs begins as data are gathered. Some qualitative researchers defer the literature review until after data collection and analysis to avoid biasing their analysis and interpretation of the data. Most often, qualitative researchers review the literature at the beginning of the process to establish the need for the study. Qualitative researchers who use frameworks during study development must maintain intellectual honesty to prevent the theoretical perspective from obscuring the perspectives of the participants. The decision about whether to identify a theoretical perspective should be consistent with the research approach chosen. Hypotheses are not appropriate for qualitative studies because hypotheses specify outcomes of studies and variables that are to be manipulated or measured. This approach to a study is not consistent with the philosophical orientation of qualitative research. Qualitative researchers may identify research objectives or questions to connect the purpose of the study to the plan for data collection and analysis. Because qualitative research is more open-ended and the focus is on participants’ perspectives, qualitative researchers may not specify research objectives or research questions in order to avoid prematurely narrowing the topic. It is unusual for a qualitative researcher to articulate the principal research question in a research report. The sample for a rigorous qualitative study is not as large as the sample for a rigorous quantitative study. The researcher stops collecting data when enough rich, meaningful data have been obtained to achieve the study aims. Data saturation, sometimes termed theoretical saturation, is the point at which new data begin to be redundant with what has already been found, and no new themes can be identified. In qualitative research, immersion in the data before the analysis process has been referred to as dwelling with the data. DIF: Cognitive Level: Synthesis 3. Which of the following are accurate statements about the interview process used by

qualitative researchers? (Select all that apply.) a. During the interview, participants should be discouraged from talking about anything that is not on the interview schedule. b. In qualitative research, the interview is a cooperative and interactive process. c. The interviewer should dress in either business attire or a nursing uniform when conducting interviews or focus groups. d. When a study participant cries or expresses strong emotion, the researcher should stay with the person and display empathy while listening to what the participant has to say. e. For the novice researcher, preparation for interviewing includes becoming familiar with the philosophical base of the method chosen. f. Persons experienced in qualitative interviewing can provide the novice researcher information and guidance on techniques. ANS: B, D, E, F

A researcher new to qualitative methods should read primary sources related to the method being considered and seek guidance for understanding its philosophical base. A research mentor, especially a researcher with more experience with the specific methods or topic in which the novice is interested, can be invaluable. The researcher and the participant answer the research question together through their interaction with one another. When dressing for an interview, the researcher needs to consider how the participant is likely to be dressed. Dressing in formal business attire or a nursing uniform may emphasize the power differences in the relationship. Dressing too casually may be viewed as an indication that the interaction is not important to the researcher. Power issues may affect the effectiveness of the interview. Visual neutrality is important, as well, in clothing colors. The qualitative interview is not about the researcher; it’s about the participant. The researcher emphasizes that by de-emphasizing himself or herself. Olfactory neutrality is important, for the same reason. As nurses do for patient care, researchers should avoid cologne, perfume, and other strong smells. Emotional expression during an interview may be expected, depending on the topic. Participants who become visibly upset while telling their story should be asked, “Do you want to pause the interview for awhile while you take a deep breath and compose yourself?” or even, “You seem upset. Do you want to end this interview, or do you want to proceed?” When the participant becomes distressed or overcome with emotion, however, the researcher may choose to turn off the recording device and stop the interview completely for a few minutes. The researcher may be able to continue if the participant is able to become composed. The researcher should stay with the upset participant. It is important to recognize topics that are more likely to be distressing and have a plan developed for emergency assistance, if needed, or a list of mental health professionals available if support or a referral is needed. DIF: Cognitive Level: Synthesis 4. The role of the facilitator in focus group qualitative interviewing involves many techniques

and skills. Indicate which of the following are appropriate to the role. (Select all that apply.) a. To question or challenge ideas and increase group interaction, once rapport has been established b. To moderate the discussion c. To contribute to the discussion d. To ask participants to justify their positions, especially for controversial content e. To use probes to elicit details, or to refocus the discussion f. To clarify, paraphrase, and reflect back what group members have said g. Late in the session, to encourage group members to go beyond the current discussion or debate and reflect on differences among the views of participants and inconsistencies within their own thinking h. Set the stage by explaining to participants what the goal of the session is ANS: A, B, E, F, G, H

The facilitator needs to understand the aims of the focus groups and to communicate these aims to the participants before the group session. Make clear to the group that the facilitator’s role is to moderate the discussion, not to contribute. The facilitator may elect to give participants some of the questions before the group meeting to enable them to give careful thought to their responses. Probes can be used to elicit richer details, by means of questions such as “How would that make a difference?” or responses such as “Tell us more about that situation.” It is important to avoid pushing participants toward taking a stand and having to defend that position. Once rapport has been established, the facilitator may be able to question or challenge ideas and increase group interaction. The researcher and/or facilitator may come to the focus groups with preconceived ideas about the topic. Early in the session, it is important to provide opportunities for participants to express their views on the topic of discussion. The facilitator may use probes or questions if the discussion wanders too far from the focus of the study. A good facilitator weaves questions into the discussion naturally. The facilitator’s role is to clarify, paraphrase, and reflect back what group members have said. Late in the session, the facilitator may encourage group members to go beyond the current discussion or debate and reflect on differences among the views of participants and inconsistencies within their own thinking. DIF: Cognitive Level: Synthesis 5. Choose the disadvantages to the use of Internet-based data collection. (Select all that apply.) a. It can be difficult to obtain consent. b. It limits the sample to those who can read and write, use computers, and have

Internet access. c. It can be used only with quantitative research methods. d. It can provide only a small number of participants. e. Fewer and fewer studies are being conducted using Internet-based data, because of

security concerns. ANS: A, B

Quantitative researchers are regularly using Internet-based surveys and instruments to gather data, but qualitative researchers also use Web-based communities such as online forums and blogs for research purposes. The number of participants available for Internet-based research is extensive but does have the limitation that samples include only those who can read and write, are comfortable using a computer, and have access to the Internet. Researchers have noted in these studies that one of the limitations was that the data represent only those who have Internet access and are comfortable describing personal experiences in the online forum. There are issues related to obtaining consent, as well. Studies will continue to be conducted using the Internet, because researchers aware of the issues can develop studies to minimize such concerns. DIF: Cognitive Level: Analysis

Chapter 13: Outcomes Research Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. Sampling in outcomes studies differs from that in traditional quantitative research in several

ways. Which is true regarding sampling in outcomes studies? a. A heterogeneous sample is preferred. b. A random sample is required. c. A small, focused sample is artificially assembled. d. The sample is selected before an intervention occurs. ANS: A

Donabedian recommended use of huge databases in outcomes research so that, at the analysis level, connections among variables would be apparent. Because of its nature, outcomes research depends heavily on correlational evidence. In contrast to the type of sampling seen in the quantitative methodology, descriptive and correlational outcomes research tends to use an entire data set for establishment of basic measured values, as well as examination of trends over time. In this case, the sample includes the entire accessible population. Random sampling is used infrequently, primarily for initial testing of interventions designed to impact outcomes. When using an entire database, heterogeneous samples result, enabling generalization to that same accessible population. DIF: Cognitive Level: Comprehension 2. What does “a preference for Type I error, as compared with Type II error” in outcomes

research mean? a. The outcomes researcher is not particularly concerned with drawing incorrect conclusions. b. The outcomes researcher would rather identify a possible connection that doesn’t end up being true than miss something. c. The outcomes researcher would rather establish definite causation than an indefinite connection. d. Patients usually don’t recognize what quality of care really is. ANS: B

On a methodological level, Donabedian stressed that when performing research on healthcare quality, Type I error should be preferred to Type II error: in other words, sample sizes should not be small, and level of significance should be set high enough to achieve possibly erroneous positive results with moderate samples. This was quite divergent from the medical research practices of the time, in which levels of significance were set at 0.01 to 0.05. In a Type I error, the null hypothesis is rejected when it is true; this means that occasionally positive findings will not be found statistically significant, on replication. DIF: Cognitive Level: Synthesis 3. A researcher is studying the likely occurrence rate of secondary cancers after a new schedule

of chemotherapy for childhood leukemia, using a biochemical marker obtained by blood draw 6 months after the initiation of chemotherapy. What is the rationale for using this biological marker as a proximate outcome, rather than counting the actual rate of secondary cancers?

a. It could be psychologically harmful to children and families to have researchers

following up in the future to ask whether the child has had a cancer recurrence. b. The final end point is not obtainable over a reasonable span of time, since

secondary cancers can occur at any age through late adulthood. c. There is no viable rationale for this decision. Most proximate end points are

unreliable variables and should not be used unless there are no final end points. d. The researcher is not interested in whether children suffer a secondary malignancy;

the researcher is merely interested in the biological marker’s value. ANS: B

Proximate end points are clinical goals occurring earlier in the process of treatment than the final end point. They allow an earlier evaluation to be made, relative to a structure or process of interest. DIF: Cognitive Level: Analysis 4. Which description indicates research that is a prospective cohort study? a. All of the children in Toledo, Ohio, are weighed and measured to obtain an

accurate statistic for malnutrition occurrence. b. A physician’s records are analyzed to identify how many of the patients have

remained in the physician’s care for more than 20 years. c. The citizens of a city experiencing a nuclear accident are tracked for cancer

occurrence. d. A database is accessed to identify mortality rate in patients with sepsis. ANS: C

Prospective cohort studies, which originated in the field of epidemiology, use a descriptive, or occasionally correlational, longitudinal design. The researcher identifies a group of persons at risk for experiencing a particular event and follows that same group over time, collecting data at intervals. Sample sizes for these studies must be large when only a small portion of the at-risk group will experience the event. The entire group is followed and multiple measurements obtained, often using dichotomous variables. Gradations of outcomes, both before and after confirmation of event occurrence, also can be determined DIF: Cognitive Level: Comprehension 5. A hospital has recently converted to an “80% BSN staff” policy. In service of this goal, all

newly hired nurses are expected to hold at least a bachelor’s degree in nursing. Within the area of outcomes research, the variable “educational preparation of nurses” is what kind of a variable? a. Practice profile b. Outcome of care c. Process of care d. Structure of care ANS: D

Structures of care are elements of organization and administration, as well as provider and patient characteristics, that exist prior to care and may affect outcomes. Some structures of care are the overall organization and administration of the healthcare agency, the essential equipment of care, educational preparation of qualified health personnel, staffing, and workforce size, as well as patient characteristics and the physical plant of the agency within its neighborhood. Practice profiling is an epidemiological technique that focuses on patterns of care. It can be used to compare outcomes between healthcare professionals’ practices, in comparison with those of similar providers or with accepted standards of practice. Processes of care address the actual care delivered by healthcare persons both in a technical sense, as reflected by standards of care and individual performance, and in relation to patient-practitioner interactions with patients. Although technical care is measurable, patient-practitioner interactions are more difficult to evaluate. Processes also address the promptness with which care is instituted, as well as patient inclusion in decision-making and choices. Outcomes are, generally speaking, improvement in health and satisfied clients, usually operationalized as proximate end points, clinical end points, satisfaction with care, and general well-being. DIF: Cognitive Level: Application 6. A study examines the careers of hospital nurses who have opted for retirement before the age

of 55, identifying their education, work shift, final work area, and the religion in which they were raised. This is an example of which type of study? a. Prospective cohort b. Cost-effectiveness analysis c. Population-based d. Retrospective cohort ANS: D

A retrospective cohort study is an epidemiological design, in which the researcher identifies a group of people who have experienced a particular event or outcome in the present or the recent past. Data are obtained from existent records or previously collected data, predating the occurrence of the event. A prospective cohort study also uses an epidemiological design in which a group of people are identified who are at risk for experiencing a particular event. A population-based study uses a sample derived exclusively from the population of interest and ultimately applied to that same population. The cost-benefit analysis compares costs and benefits, in terms of some single unit of analysis. When a cost-benefit analysis uses money for the unit of analysis, it is referred to as a cost-effectiveness analysis. DIF: Cognitive Level: Application 7. A nurse manager designs a research study to examine nurse workload stress, work shift,

number of years in the nursing profession, number of medication errors, patient falls, and after-shift overtime, as they relate to one another. What is the most likely method the manager will use to study this? a. Multilevel analysis b. Analysis of improvement c. Analysis of variance d. Analysis of change ANS: A

Multilevel analysis is merely use of more than one way to analyze a data set. In outcomes research, an unexpectedly positive outcome may be associated with increases or decreases in certain structural or processual variables. Multilevel analysis is the statistical technique that allows the researcher to tease out various different factors that seem promising in predicting an outcome. Variance analysis in outcomes research, in practice, is a lot less like arithmetic than it sounds. It is merely a strategy that defines expected outcomes, and the times they will occur, and then tracks delay or nonachievement of these outcomes. Delays and nonachievements are called variances. Analysis of change is used in trend analysis studies to determine change and rate of change over time. Analysis of improvement is a directional version of analysis of change. Because statistical tests for analysis of improvement focus on only one direction, statistical significance may be reached with smaller samples than for analysis of change. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. Outcomes research differs from traditional quantitative research in which of the following

ways? (Select all that apply.) a. Its theoretical framework is Donabedian’s paradigm. b. It uses designs that no other methodology uses. c. Its publications always have “outcomes” in the titles. d. It focuses on quality. e. Its dependent variables are measures of outcomes. ANS: A, D, E

We consider outcomes research a distinct methodology because of three attributes: its unique focus upon quality as described by Donabedian, its theoretical framework, and its shared dependent variable (various markers of quality). These and other aspects that distinguish outcomes research are presented here. Unlike the qualitative and mixed methods methodologies, the outcomes research methodology does not possess its own exclusive array of distinct designs. In terms of methodology and design, outcomes research uses the quantitative methodology and some of the quantitative designs. Within this design cluster, most of its designs are correlational and descriptive. The vast majority of outcomes research data is obtained retrospectively. Researchers conducting outcomes studies do not always state, “This is outcomes research.” Although many studies that can be considered outcomes research do not contain the word outcome in their titles, most of these can be accessed using the word outcome as a search term. DIF: Cognitive Level: Synthesis 2. In nursing, modern outcomes research is likely to focus upon which of the following topics?

(Select all that apply.) a. Variables of the nurse, such as burnout, stress, or factors that affect nursing care b. Qualitative aspects of the patient experience, such as symptoms and meaning c. Workplace issues, such as work satisfaction, staffing, skill mix, the physical plant, managerial style, and healthcare team interactions d. Structures of care, such as educational and specialty preparation of the nurse or the other members of the healthcare team e. Adverse patient outcomes, and disciplinary actions of the nurse and other members

of the healthcare team f. Measurements of patient illness, wellness, functionality, or safety ANS: A, C, D, F

Donabedian developed a theory of how to assess the quality of health care, by examining its structures, processes, and outcomes, called “the Donabedian paradigm.” Structures of care are set entities that affect quality of care in a healthcare environment. Some structures of care in recent research are nursing management of the hospital unit, educational preparation of qualified health personnel, staffing, and workforce size, as well as the physical plant of the agency within its neighborhood. Processes of care address the actual care delivered by healthcare persons both in a technical sense, as reflected by standards of care and individual performance, and in relation to patient-practitioner interactions with patients, and they may address patient satisfaction, burnout, behaviors of the members of the healthcare team, and decisions of nurses in a setting with less than optimal staffing. Outcomes are measured as clinical end points, satisfaction with care, functional status and general well-being. DIF: Cognitive Level: Synthesis 3. Why would outcomes research use an entire database, rather than merely selecting a sample?

(Select all that apply.) a. Use of the whole database provides an analysis that addresses the entire patient population. b. Permission to use an entire database implies that the entire database must be studied. c. Small effect sizes and multiple variables demand huge samples, if statistical significance is to be achieved. d. Periodic review of the entire database makes it possible for the researcher to identify patterns related to outcomes that might be missed if only part of the database were used. e. Cost is not an issue. ANS: A, C, D

Donabedian recommended use of huge databases in outcomes research so that, at the analysis level, connections among variables would be apparent. Because of its nature, outcomes research depends heavily on correlational evidence. Early in his work, Donabedian stressed the importance of periodic review of data and of paying attention to patterns within the data set. He described this as a continuous loop using the review process, which later evolved into continuous quality improvement (CQI). Some effects discerned in large-sample database data are subtle, so it is essential to calculate the needed sample size for a given effect size, using power analysis. When the effect is subtle (small), large samples are required, and an entire database is more likely to show statistical significance than is part of one. DIF: Cognitive Level: Synthesis 4. From what common sources does outcomes research draw its data? (Select all that apply.) a. Journals kept by clients undergoing treatment for a chronic ailment b. Nurses’ electronic charting within a single hospital c. A multi-hospital system’s morbidity and mortality reports d. A health insurance company’s records e. A state disability agency’s records

ANS: B, C, D, E

One source of samples used for outcomes studies are large databases. Two broad categories of databases emerge from patient care encounters: clinical databases and administrative databases. Clinical databases are created by hospitals, healthcare providers, and researchers. Everything charted during the patient stay is retained in a clinical database. Administrative databases are created by insurance companies, government agencies, and others not directly involved in providing patient care. DIF: Cognitive Level: Application 5. Outcomes research in a hospital could address interactions among which of the following

general groups of variables? (Select all that apply.) a. Those that existed prior to treatment, such as narrative health histories b. Those that reflect surroundings, such as the size of family waiting rooms c. Those that reflect perceived outcome, such as quality of life d. Those that pertain to staff, such as levels of education and training e. Those that reflect physical outcome, such as patient survival ANS: B, C, D, E

Donabedian developed a theory of how to assess the quality of health care, by examining its structures, processes, and outcomes, called “the Donabedian paradigm.” Structures of care are set entities that affect quality of care in a healthcare environment. Some structures of care in recent research are nursing management of the hospital unit, educational preparation of qualified health personnel, staffing, and workforce size, as well as the physical plant of the agency within its neighborhood. Processes of care address the actual care delivered by healthcare persons both in a technical sense, as reflected by standards of care and individual performance, and in relation to patient-practitioner interactions, and they may address patient satisfaction, burnout, behaviors of the members of the healthcare team, and decisions of nurses in a setting with less than optimal staffing. Outcomes are measured as clinical end points, satisfaction with care, functional status, and general well-being. DIF: Cognitive Level: Synthesis 6. In an outcomes study of nurse satisfaction in the workplace, which of the following would be

reasonable outcome measures? (Select all that apply.) a. Lunch relief staffing b. Formal complaints filed by nurses c. Nurse satisfaction surveys d. Manager style e. Patient survival f. Nurses’ average length of employment g. Sick calls h. Reported workload stress ANS: B, C, F, G, H

Outcomes were defined by Donabedian as improvement in health and satisfied clients, and described in his other publications as clinical end points, satisfaction with care, and general well-being. If nurse satisfaction is the outcomes measure, the researcher must measure something having to do with nurse satisfaction, discontentedness with the job, contentedness with the job, turnover, nurse mental health, or nurse stress.

DIF: Cognitive Level: Analysis 7. Which of the following are processes of care within a hospital that are likely to be scrutinized

in research focusing on nursing-sensitive patient outcomes? (Select all that apply.) a. Cost of hospital insurance b. The ways nurses perform a certain task of patient care c. Whether there are policies governing a procedure d. Educational preparation of nurses e. Nursing workload f. Number of hospital beds ANS: B, C, D, E

In current hospital quality improvement research, a nursing-sensitive patient outcome (NSPO) is one influenced by nursing care decisions, actions, or attributes. It may not be caused by nursing but is associated with nursing. For outcomes research in which nurses function as structures (nursing educational preparation, for example) or as processes (technical capability), aggregates are used in data analysis. Outcomes are scrutinized so as to reveal connections with structures or processes. Hypotheses are formed. Changes in structures and processes are tracked, so as to demonstrate trends. Ultimately, changes in processes are mandated, and the results measured. Sometimes structural modifications take place, if enough evidence is accrued. For instance, changes in standards of care can be made, in response to the body of evidence. The institution determines numbers of nurses, salaries, educational levels of nurses, assignments of nurses, workload of nurses, management of nurses, and policies related to nurses and nursing practice. It might even include the physical plant of the nursing unit, such as whether there is a sequestered area on a nursing unit, in which nurses can prepare medications. DIF: Cognitive Level: Application 8. How do practice pattern profiling and nursing-sensitive patient outcomes research relate to

one another? (Select all that apply.) a. The identification of nursing-sensitive patient outcomes is a type of practice pattern profiling. The purpose of both is to identify the outlier, so as to improve patient outcomes. b. Practice pattern profiling scrutinizes an individual in comparison with a group; nursing-sensitive patient outcomes research addresses nurses as a group, rather than as individuals. c. Both can identify variables that affect patient outcome. d. Both pose risk to the person who delivers care. e. Neither can be undertaken without signed consent from the participants. f. Both are types of outcomes research. ANS: B, C, F

In current hospital quality improvement research, a nursing-sensitive patient outcome (NSPO) is one influenced by nursing care decisions, actions, or attributes. It may not be caused by nursing, but is associated with nursing. Practice pattern profiling is an epidemiological technique that focuses on patterns of care rather than individual occurrences of care. Researchers use large database analysis to identify a provider’s pattern of practice and compare it with that of similar providers or with an accepted standard of practice. The technique has been used to determine overutilization and underutilization of services, to examine costs associated with a particular provider’s care, to uncover problems related to efficiency and quality of care, and to assess provider performance. Both use existent databases as data sources, a majority of the time. DIF: Cognitive Level: Comprehension 9. An advertisement maintains that zip code affects length of life. If outcomes research were

designed to explore this geographical difference, what variables would be most useful in understanding the outcome of length of life? (Select all that apply.) a. Other outcome variables, such as quality of life and consumer perceptions b. The availability of parking near clinics, a structural variable c. The time it actually takes in both areas to transport a patient to an emergency room, a structural variable d. The prevalence of ethnically associated health problems, a structural variable e. Physicians’ clinical judgment, a process variable f. The presence of standard nursing care plans in the hospitals, a process variable g. The number of specialist physicians per 1000 population in each area, a structural variable h. The number of primary care physicians per 1000 population in each area, a structural variable ANS: C, D, E, G, H

Geographical analysis is an epidemiological strategy that examines variations in health status, health services, patterns of care, or patterns of use by geographical area. Geographical analyses are sometimes referred to as small area analyses. Variations may be associated with sociodemographic, economic, medical, cultural, or behavioral characteristics. Locality-specific factors of a healthcare system, such as capacity, access, and convenience, may play a role in explaining variations. The social setting, environment, living conditions, and community also may be important factors. In this example several of the variables listed pertain to length of life: transport time for emergencies, ethnicity as it predicts health problems, and the quality and quantity of physicians for the population. DIF: Cognitive Level: Comprehension 10. What are the differences between a cost-effectiveness analysis and a cost-benefit analysis?

(Select all that apply.) a. Cost-effective analysis is prospective, and cost-benefit analysis is retrospective. b. Cost-effectiveness analysis in outcomes research focuses on health outcomes, whereas cost-benefit analysis may or may not focus on health outcomes. c. Cost-benefit analysis addresses cost as the opposite of benefit, whereas cost-effectiveness analysis treats cost as a limited resource. d. Cost-benefit analysis does not consider anything except financial cost, whereas cost-effectiveness analysis considers intangible costs as well.

e. Cost-effectiveness analysis always considers financial cost as one of its variables,

whereas cost-benefit analysis may or may not do so. ANS: B, C, E

The most widely used term in discussion of cost is the cost-benefit analysis. In general, cost-benefit analysis is analogous to Donabedian’s concept of optimality, in that it involves comparison of costs and increased benefits, in terms of some single unit of analysis. In financial systems, the unit is money. However, in medical epidemiology, various other units of analysis may be selected, as well as cost, such as lives, disability, missed work days, number of vials of vaccine used, or extent of visible scarring. When a cost-benefit analysis uses money for the unit of analysis, it is often referred to as a cost-effectiveness analysis. DIF: Cognitive Level: Application 11. A complete appraisal of quality of care in an institution is undertaken. It could justifiably be

linked with which of the following? (Select all that apply.) a. The types of insurance the hospital accepts b. The general safety of the hospital grounds for visitors and family c. Advertisements for health care in the area d. Numbers of complaints the hospital administrator receives e. Nurse: patient staffing ratios f. National research funding for health care g. Measures of physiological function, 12 weeks after surgery ANS: B, D, E, G

Donabedian developed a theory of how to assess the quality of health care, by examining its structures, processes, and outcomes, called “the Donabedian paradigm.” Structures of care are set entities that affect quality of care in a healthcare environment. Some structures of care in recent research are nursing management of the hospital unit, educational preparation of qualified health personnel, staffing adequacy, and workforce size, as well as the physical plant of the agency within its neighborhood. Outcomes are measured as clinical end points, satisfaction with care, functional status, and general well-being. Satisfaction can be measured using the number of complaints received by administration. DIF: Cognitive Level: Analysis 12. A researcher performs a study in which data are obtained from 10 years of notes made by

physicians and nurse practitioners in a large, shared urban obstetrical practice. The researcher collects the following data: primary person providing health care, person attending the delivery, patient’s age, patient’s parity, patient zip code, baby’s Apgar scores, gestational age at first appointment, gestational age at delivery, and maternal complications. What type of research could this be? (Select all that apply.) a. Geographical analysis b. Outcomes research c. Qualitative research d. Mixed methods research e. Quantitative research f. Prospective research g. Retrospective research h. Practice pattern profiling

ANS: A, B, E, G, H

Geographical analysis is an epidemiological strategy in which variations in health status, health services, patterns of care, or patterns of use by geographical area are analyzed. Outcomes research is globally defined as research that investigates the outcomes of care, relating them to attributes of care delivery. Qualitative research is a scholarly approach used to describe life experiences, cultures, and social processes from the perspectives of the persons involved. Mixed methods research is a research methodology in which two research designs are utilized, one quantitative and one qualitative, in order to better represent truth. Formal, objective, systematic study process that counts or measures, in order to answer a research question. Its data are analyzed numerically. Quantitative research counts or measures, in order to answer a research question. A prospective study is one in which a group of people are identified who are at risk for experiencing a particular event, and are then followed over time. A retrospective study is one in which a group of people who have experienced a particular event or outcome in the present or the recent past are identified. Data are obtained from existent records or previously collected data, predating the occurrence of the event. Practice pattern profiling is an epidemiological technique that focuses on patterns of care. It was used originally in healthcare research to compare the outcomes of one physician’s practice with norms or averages among other physicians. The technique has been used to determine overutilization and underutilization of services, to examine costs associated with a particular provider’s care, to uncover problems related to efficiency and quality of care, and to assess provider performance. DIF: Cognitive Level: Synthesis

Chapter 14: Mixed Methods Research Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. What is the best research approach for investigating the actual representation of Hispanic

managers within healthcare institutions and the workplace beliefs and prejudices that perpetuate their disproportionate representation? a. Mixed methods approach b. Quantitative approach c. Qualitative approach d. Outcomes approach ANS: A

Mixed methods research is conducted when the study problem and purpose are best addressed using two research designs, almost always one quantitative and one qualitative. Quantitative research counts or measures, in order to answer a research question. Qualitative research is a scholarly approach used to describe life experiences, cultures, and social processes from the perspectives of the persons involved. Outcomes research examines quality of care, as quantified by selected outcomes, utilizing predominantly non-interventional quantitative designs from epidemiology and other disciplines. DIF: Cognitive Level: Synthesis 2. What is the principal disadvantage of mixed methods research? a. Its results are impossible to integrate, so interpretation is highly subjective. b. Because of its complexity, researchers from different research traditions must be

called upon to collaborate, in order to conduct the study. c. The time required to complete a mixed methods study is more than that which

would be required for completing one that utilizes only one method. d. Quantitative data usually are converted to qualitative data before analysis or

interpretation, so that a cohesive analysis can be accomplished. ANS: C

Mixed methods research requires a longer period of time and more resources than would be needed for single-method studies. The motivation for the study and the desired outcome determine the best way to integrate the data of a mixed methods study. It is sometimes possible to assemble a research team of health professionals with different education and experiences, each one of which is responsible for a portion of a study. Individual researchers may hire a consultant to provide guidance for the component of the study with which the researcher is less familiar. Quantitative and qualitative data usually are combined during analysis or interpretation. DIF: Cognitive Level: Synthesis 3. In a study of pain control and fatigue after hip replacement, what would the primary

advantage be of conducting a quantitative descriptive portion followed by a grounded theory portion? a. The results would be more difficult to understand but more scholarly. b. It would force a multiple-authorship arrangement, assisting each scholar.

c. The researcher’s analyses and interpretations will be of higher quality. d. The time required to complete the study would be approximately double that of

completing one that utilized only one method. ANS: C

Using mixed methods studies offers researchers the ability to utilize the strengths of both qualitative and quantitative research designs to answer different stages or parts of a complex research question. Hence, the method is selected to best answer the research question, not because it is considered more scholarly than other research methods. It is sometimes possible to assemble a research team of health professionals with different education and experiences, each one of which is responsible for a portion of a study. On the other hand, individual researchers may hire a consultant to provide guidance for the component of the study with which the researcher is less familiar: there need not be more than one author, under that condition. Qualitative examination of the phenomenon facilitates a fuller understanding and is well suited to explaining and interpreting relationships. Mixed methods studies require time commitment that may exceed that required for single-method studies. DIF: Cognitive Level: Application 4. A nurse researcher is interested in the work of public health nurses (PHNs). The researcher

first performs a qualitative phase of the study in which PHNs are interviewed about the skills and abilities needed for PHN practice. Data are analyzed, and themes are identified. In the next phase, the researcher creates a survey utilizing the themes derived from the interviews; the survey lists each skill with a Likert-type scale to rate the use and importance of the skill in PHN practice. Hundreds of PHNs complete the survey, and the quantitative data are analyzed. What is the best description of the type of mixed methods strategy employed by the researcher? a. Exploratory sequential strategy b. Explanatory sequential strategy c. Convergent concurrent strategy d. Methodological triangulation ANS: A

The exploratory sequential strategy begins with collection and analysis of qualitative data, followed by collection of quantitative data. Often, findings of the qualitative data analysis are used to design the quantitative phase. This strategy may be used to design a quantitative tool. When using an explanatory sequential strategy, the researcher collects and analyzes quantitative data, and then collects and analyzes qualitative data to explain the quantitative findings. The convergent concurrent strategy is selected when a researcher wishes to use quantitative and qualitative methods in an attempt to confirm, cross-validate, or corroborate findings within a single study, using a single sample. This model generally uses separate quantitative and qualitative methods as a mechanism to allow the strengths of the two methods to complement each other. Therefore, quantitative and qualitative data collection processes are conducted concurrently. Historically, methodological triangulation was what mixed methods studies were first called. However, the process whereby integration of findings occurred was not well defined. DIF: Cognitive Level: Application

5. A nurse at the local clinic notices that adherence to the treatment regimen for seizure disorder

is more problematic in patients from one cultural group. The nurse develops a research team to explore this problem. The group plans to collect data via focus group interviews and questionnaires administered to participants at the time of the interviews. What is the best description of the type of mixed methods strategy employed by the researcher? a. Exploratory sequential strategy b. Explanatory sequential strategy c. Convergent concurrent strategy d. Methodological triangulation ANS: C

The exploratory sequential strategy begins with collection and analysis of qualitative data, followed by collection of quantitative data. Often, findings of the qualitative data analysis are used to design the quantitative phase. This strategy may be used to design a quantitative tool. When using an explanatory sequential strategy, the researcher collects and analyzes quantitative data and then collects and analyzes qualitative data to explain the quantitative findings. The convergent concurrent strategy is selected when a researcher wishes to use quantitative and qualitative methods in an attempt to confirm, cross-validate, or corroborate findings within a single study, using a single sample. This model generally uses separate quantitative and qualitative methods as a mechanism to allow the strengths of the two methods to complement each other. Therefore, quantitative and qualitative data collection processes are conducted concurrently. Historically, methodological triangulation was what mixed methods studies were first called. However, the process whereby integration of findings occurred was not well defined. DIF: Cognitive Level: Comprehension 6. A nurse is interested in learning more about a topic of interest. The nurse finds a published

study on the topic that utilized a mixed methods strategy. The researchers for this mixed methods study found overwhelming similarities between the qualitative and quantitative results of the study. The nurse then finds two more studies on the same topic—one quantitative and one qualitative—in which the researchers reported divergent findings from each other and from the mixed method study results. What is the best explanation for why the mixed methods research results were similar but results of the two separate studies were different? a. Methodological rigor is higher for mixed methods studies. b. There is no room for individual interpretation in qualitative research, so the researcher must have made an error. c. The mixed methods study results were derived from the same study participants. d. Each of the studies had unique philosophical underpinnings, which likely influenced the kinds of questions that were posed. ANS: D

While mixed methods research may be rigorous, it is not automatically more rigorous than any other quantitative methods study. When members of different professions comprise a team, disagreements may arise when each member is biased to the superiority of his or her preferred method, leading to minimization or negation of the findings of the other method. The means of integration can be a particularly difficult issue unless the team’s philosophical foundation was discussed during the design phase. It is plausible that different research teams using varied research methods may come to alternate, yet valid, conclusions influenced by the team’s shared philosophical beliefs. The philosophical basis of qualitative research is interpretive, humanistic, and naturalistic and is concerned with helping those involved to understand the meaning of their social interactions. A mixed methods study may or may not utilize the same participants for each arm of data collection, depending on the type of strategy chosen. For example, focus groups may be conducted with the members of target population and items for the quantitative tool developed using phrases and content generated qualitatively. The quantitative tool could then be administered to a different group of study participants. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. Quantitative experimental researchers often “brainstorm” after each study, discussing the

findings with colleagues, in order to interpret them and create new theories and strategies for testing them. Then they proceed to the next study. This is similar to a sine wave—first quantitative, then qualitative, and then quantitative, and so on. This represents an informal and ongoing combination of what research strategies? (Select all that apply.) a. Mixed methods b. Explanatory sequential c. Blocking d. Multiple causality e. Content analysis f. Exploratory sequential g. Convergent concurrent ANS: A, B, F

Mixed methods research is conducted when the study problem and purpose are best addressed using two research designs, almost always one quantitative and one qualitative. A research process in which quantitative and qualitative inquiry alternate is essentially mixed methods research with formal publication of only the quantitative pieces. When using an explanatory sequential strategy, the researcher collects and analyzes quantitative data and then collects and analyzes qualitative data to explain the quantitative findings. The exploratory sequential strategy begins with collection and analysis of qualitative data, followed by collection of quantitative data. Often, findings of the qualitative data analysis are used to design the quantitative phase. The randomized block design, also called randomized blocking, uses the classic experimental design most frequently, but it adds the feature of blocking, which is making random assignment in two or more stages. Multiple causality refers to the case in which two or more variables combine in causing an effect. Content analysis is a method in which the researcher classifies the words in a text into categories. The convergent concurrent strategy is a mixed methods approach in which the researcher collects quantitative and qualitative methods at the same general time in a single sample, in an attempt to confirm, cross-validate, or corroborate findings. DIF: Cognitive Level: Synthesis 2. A group of researchers investigate pet therapy use in the rehabilitation of traumatic brain

injury survivors. The published results matrix displays convergence between the qualitative theme of “not being alone” and the quantitative result “external support.” Additionally, the matrix reveals divergence between the qualitative theme of “starting anew” and the quantitative result “sadness.” What do these findings tell the reader? (Select all that apply.) a. The quantitative results were obtained before the qualitative results. b. The participants valued “not being alone” and “external support” similarly. c. This was an exploratory sequential study. d. Differences were noted between “starting anew” and “sadness.” e. The quantitative results in mixed methods research always represent frequency counts generated from the qualitative interviews. ANS: B, D

The convergent concurrent strategy is selected when a researcher wishes to use quantitative and qualitative methods in an attempt to confirm, cross-validate, or corroborate findings within a single study, using a single sample. This model generally uses separate quantitative and qualitative methods as a mechanism to allow the strengths of the two methods to complement each other. Therefore, quantitative and qualitative data collection processes are conducted concurrently. This strategy usually integrates the results of the two methods during the interpretation phase, and convergence strengthens the knowledge claims or explains lack of convergence. A convergent concurrent study table may present results in a matrix format, denoting points of convergence (similarity) and divergence (difference) between the qualitative and quantitative data. Some researchers support converting the data from one arm of the study to the same type as the other arm: essentially, this means using qualitative data to generate (quantitative) counts of frequency with which various codes or themes occurred. However, this would not be the case for all studies that use a convergent concurrent strategy. DIF: Cognitive Level: Analysis 3. What are valid reasons for selecting an exploratory sequential strategy research design?

(Select all that apply.)

a. The researcher is interested in both the relative occurrence of a phenomenon and

the meanings ascribed to it. b. On a two-person research team, each researcher is schooled in either qualitative or

quantitative research methods. c. There is little known about the topic, yet the researcher wants to be able to perform

hypothesis testing. d. The researcher is concerned that collection of quantitative data may bias data

collected qualitatively. e. The researchers expect to collect quantitative and qualitative data all at once. ANS: A, C, D

One reason to use this strategy is to collect data about patient perspectives concerning an issue or problem, so that the patients’ points of view are represented. With this input, an intervention can be developed or refined, too, incorporating the patients’ perspectives about the intervention. An exploratory sequential strategy may be indicated when a topic has not been studied previously. It is sometimes possible to assemble a research team of health professionals with different education and experiences, each one of which is responsible for a portion of a study. Individual researchers may hire a consultant to provide guidance for the component of the study with which the researcher is less familiar, allowing a sole researcher to conduct the study. Mixed methods studies require time commitment that may exceed that required for single-method studies. Exploratory sequential designs may be used when the researcher wants to expand on what is known about a phenomenon and the researcher does not want the content of the quantitative instruments to bias data collected qualitatively. These designs are used when the researcher needs insight into participants’ perspectives prior to finalizing the quantitative component: they represent explanation of a phenomenon, followed by quantification. DIF: Cognitive Level: Application 4. In a research study, burn patients either washed their own wounds or had them washed by

nursing staff daily. Patients performed self-washing on alternate days. Pain was measured at intervals during dressing changes. Patients also were interviewed near the end of hospitalization, after all dressing change data had been collected, and analyzed from the theoretical perspective of symbolic interactionism, in order to determine what factors had made their pain more severe or less severe, under each condition. What study designs were used in this research project? (Select all that apply.) a. Grounded theory research b. Explanatory sequential strategy c. One-group pretest-posttest design d. Mixed methods research e. Time series repeated reversal design ANS: A, B, D, E

Mixed methods research is a methodology that combines two designs, usually one quantitative and one qualitative, into one study. In an explanatory sequential mixed methods study, the researcher collects and analyzes quantitative data and then collects and analyzes qualitative data to explain the quantitative findings. The philosophy underlying the qualitative design of grounded theory research is symbolic interactionism. In the single-group pretest-posttest design, measurement is obtained for a single group, followed by an intervention and a second measurement of the dependent variable in that same group. The time series with repeated reversal design is just as successful as the time series design with comparison group in controlling for threats to internal validity, because subjects are measured repeatedly over time, and they act as their own controls. In this design, data usually are interpreted within subjects, analyzing whether the treatment was effective at a statistically significant level for each single subject. DIF: Cognitive Level: Synthesis

Chapter 15: Sampling Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A researcher is studying sleep habits of household cats that belong to families with small

children. The families live in urban areas. In this study, what is/are the element(s)? a. Small children b. Household cats c. Families d. Sleep ANS: B

The individual units of the population and sample are called elements. An element can be a person, event, behavior, or any other single unit of study. DIF: Cognitive Level: Analysis 2. A researcher wants to maximize the generalizability of a planned experimental study’s results.

What can the researcher do to achieve this goal, relative to sampling? a. Select a sample larger than that recommended by power analysis. b. Purposively select a sample that is extremely heterogeneous. c. Use random assignment. d. Use random sampling. ANS: D

Random sampling increases the extent to which the sample is representative of the target population. Good representativeness enhances generalizability of the results. DIF: Cognitive Level: Analysis 3. A researcher studies spending habits of teenagers in shopping malls. The researcher visits two

local malls to solicit participants. From what kind of population has the researcher selected the sample? a. The accessible population b. The entire population c. The target population d. The hypothetical population ANS: A

An accessible population is the portion of the target population to which the researchers have reasonable access. The sample is obtained from the accessible population by a particular sampling method, such as simple random sampling. The entire population is a particular group of people who share one or more characteristics that are the focus of the research. The target population is the entire set of individuals or elements meeting the sampling criteria. The hypothetical population assumes the presence of a population that cannot be defined according to sampling theory rules, which require a list of all members of the population. DIF: Cognitive Level: Application

4. A researcher selects a sample in this way. The researcher paints numbers on 100 ping-pong

balls and paints half of the balls blue and half of them green. The researcher puts the blue half onto a large tray and the green half onto another large tray. Then the researcher mixes each tray of balls and trains a dog to bring 10 balls from each tray to the researcher, gently and systematically, one at a time. What type of sample is this? a. Snowball b. Random c. Stratified random d. Systematic ANS: C

randomly by our marketing department because of your recent purchase of McCarthy’s Natural Yogurt, several organic raw vegetables, and two types of tofu. As a woman with interest in safe and healthy products, we are asking you to participate in a brief telephone survey.” What is this? a. Random sampling b. Convenience sampling c. Purposive sampling d. Systematic sampling ANS: C

In purposive sampling, sometimes referred to as purposeful, judgmental, or selective sampling, the researcher consciously selects certain participants, elements, events, or incidents to include in the study. From a sampling theory point of view, randomization means that each individual in the population should have a greater than zero opportunity to be selected for the sample. The method of achieving this opportunity is referred to as random sampling. In convenience sampling, subjects are included in the study because they happened to be in the right place at the right time. Researchers simply enter available subjects into the study until they have reached the desired sample size. Systematic sampling can be conducted when an ordered list of all members of the population is available. The process involves selecting every kth individual on the list, using a starting point selected randomly. If the initial starting point is not random, the sample is not a probability sample. Marketing research often uses product profiling to identify what consumers buy which products. A sample based on profiling is a purposive sample: people are contacted because they possess a certain pattern of purchasing. DIF: Cognitive Level: Application

6. A graduate student has a close friend who is recovering from colon cancer and has a

permanent colostomy. For the master’s thesis, the student decides to conduct qualitative research on adjustment to living with a permanent colostomy after colon cancer resection. The student asks the friend for help in recruiting participants for the research. The friend identifies a colon cancer support group to which the friend belongs and volunteers to bring a printout of the research study’s purpose and general description to the next support group meeting. If the researcher acquires all of the study participants in this way, what is the method of sampling used? a. Snowball sampling b. Cluster sampling c. Purposive sampling d. Simple random sampling ANS: A

Network sampling, sometimes referred to as snowball or chain sampling, holds promise for locating samples difficult or impossible to obtain in other ways or that had not been previously identified for study. Network sampling takes advantage of social networks and the fact that friends tend to have characteristics in common. When the researcher has found a few participants with the necessary criteria, he or she asks their assistance in getting in touch with others with similar characteristics. The first few participants are often obtained through convenience or purposive sampling methods, and the sample size is expanded using network or snowball sampling. DIF: Cognitive Level: Application 7. A researcher has already written a study proposal and performed a power analysis, which

indicates that the sample size will have to be at least 36, in order to avoid Type II error. The researcher then decides to set the level of significance at p < 0.01 rather than p < 0.05 but wants to maintain power at 0.80. What will the researcher have to do in order to maintain sufficient power? a. Increase the effect size. b. Set beta at 0.60. c. Use a different statistical test. d. Increase the sample size. ANS: D

The researcher determines the sample size needed to obtain sufficient power by performing a power analysis. Power analysis includes the standard power of 80%, level of significance (usually set at 0.05 in nursing studies), effect size, and sample size. The more stringent the significance level (e.g., 0.001 versus 0.05), the greater the necessary sample size. The effect size is determined by the magnitude of effect that the intervention produces and, consequently, cannot be adjusted. DIF: Cognitive Level: Application 8. A researcher studying depression in relation to five predictor variables decides to include five

more variables in a study because the literature reveals that they may also be involved in depression. Consequently, the researcher should do which of the following? a. Use a larger sample size. b. Set beta at a lower level. c. Perform additional reliability and validity tests.

d. Change the design of the research from correlational to descriptive. ANS: A

As the number of variables under study grows, the needed sample size may also increase. Adding variables such as age, gender, ethnicity, and education to the analysis plan can increase the sample size by a factor of 5 to 10 if the selected variables are uncorrelated with the dependent variable. DIF: Cognitive Level: Application 9. How does effect size relate to instrument sensitivity? a. If an instrument is sensitive, it will have a large effect size. b. If an instrument is not very sensitive, it will take a large effect size for the

instrument to detect a difference. c. As an instrument is better calibrated and becomes more sensitive, it increases in

effect size. d. If an instrument is extremely sensitive, it will detect a difference even when none exists; because of this effect sizes must be large. ANS: B

The smaller the effect size, the larger the necessary sample size. The effect size is a determination of the effectiveness of a treatment on the outcome (dependent) variable or the strength of the relationship between two variables. Well-developed instruments measure phenomena with precision. The more sensitive the measurement methods used in a study, the better they will detect even a small effect size. DIF: Cognitive Level: Analysis 10. A teacher is supposed to be randomly assigning students to experimental and control groups,

for participation in a learning project mandated by the school district. The teacher has an alphabetized master list of the students, numbered 1 through 30. Which is the most logical way to randomly assign the students to group? a. Put numbers 1 to 30 in a hat, draw them out one by one, and put them into alternating groups. b. Place the first 15 subjects from the alphabetized list in one group and the last 15 in the other group. c. Ignore numbers, and let the students choose their groups. d. Put numbers 1 to 30 into a hat and draw one, placing it in the experimental group. Then find a student with similar gender, attributes, and abilities, and put that one into the control group. Then go back to the hat for the next experimental subject. ANS: A

Simple random sampling is the most basic of the probability sampling methods. To achieve simple random sampling, elements are selected at random from the sampling frame. This goal can be accomplished in various ways, limited only by the imagination of the researcher. If the sampling frame is small, the researcher can write names on slips of paper, place the names in a container, mix well, and draw out one at a time until the desired sample size has been reached. Another technique is to assign a number to each name in the sampling frame. The traditional “hat draw” is a random method for selection and for assigning. Placing the students into group by the alphabet is arbitrary, not random. Allowing students to choose their groups turns the study into a quasi-experimental one. Randomly drawing only the experimental subjects one by one and then finding ones with similar attributes to go into the control group is a kind of matching, not random assignment. DIF: Cognitive Level: Application 11. Which of the following types of sampling is least common in qualitative research? a. Convenience b. Purposive c. Snowball d. Random ANS: D

Nonrandom sampling predominates in qualitative research. The five nonprobability sampling designs described in this textbook are (1) convenience sampling, (2) quota sampling, (3) purposive or purposeful sampling, (4) network or snowball sampling, and (5) theoretical sampling. These sampling methods are applied in both quantitative and qualitative research. However, convenience sampling and quota sampling are applied more often in quantitative, outcomes, and mixed methods research than in qualitative studies. Purposive sampling, network sampling, and theoretical sampling are more commonly applied in qualitative studies than in quantitative studies. DIF: Cognitive Level: Application 12. A pollster wants to obtain a large sample of voters with the least amount of trouble. Each

subject is asked to complete a pencil-paper questionnaire containing seven multiple-choice questions. Each person completing the survey receives a $1 off coupon for a regional coffee chain. The pollster decides to stand outside 20 different supermarkets for 4 hours each and ask patrons to participate in the research. Which method of sampling is this? a. Network or snowball sampling b. Purposive sampling c. Convenience sampling d. Cluster sampling ANS: C

In convenience sampling, subjects are included in the study because they happened to be in the right place at the right time. Researchers simply enter available subjects into the study until they have reached the desired sample size. Network sampling takes advantage of social networks to recruit subjects and is almost exclusively a qualitative sampling strategy. In purposive sampling, sometimes referred to as purposeful, judgmental, or selective sampling, the researcher consciously selects certain participants, elements, events, or incidents to include in the study. In purposive sampling, qualitative researchers select information-rich cases or cases that can teach them a great deal about the central focus or purpose of the study. Purposive sampling, network sampling, and theoretical sampling are more commonly applied in qualitative studies than in quantitative studies. Cluster sampling is a probability sampling method that is similar to stratified random sampling but takes advantage of the natural clusters or groups of population units that have similar characteristics. DIF: Cognitive Level: Application 13. A researcher contacts seven large hospitals and makes arrangements to recruit 55 patients

from each of their emergency rooms. If this is cluster sampling, how were the seven large hospitals chosen? a. By size b. By random selection c. By availability d. By researcher familiarity ANS: B

In cluster sampling, the researcher develops a sampling frame that includes a list of all the states, cities, institutions, or organizations with which elements of the identified population would be linked. States, cities, institutions, or organizations are selected randomly as units from which to obtain elements for the sample. In some cases, this random selection continues through several stages and is referred to as multistage cluster sampling. DIF: Cognitive Level: Application 14. “To be considered eligible for the study, subjects had to be older than 21 years of age, hold a

valid state driver’s license, and be able to fire a shotgun.” What part of the study sample description is this? a. Inclusion plan b. Population element c. Sampling criteria d. Representativeness ANS: C

Sampling criteria, also referred to as eligibility criteria, include a list of characteristics essential for membership or eligibility in the target population. The criteria are developed from the research problem, the purpose, a review of literature, the conceptual and operational definitions of the study variables, and the design. The sampling criteria determine the target population, and the sample is selected from the accessible population within the target population. DIF: Cognitive Level: Application

15. Five hundred persons were chosen to participate in a study, 270 women and 230 men,

representative of the proportion of adult women and men in the population of Portland, Oregon. Patients were selected using a table of random numbers, from a master list of all patients who had been treated for congestive heart failure (CHF) in the previous 3 months at one of Portland’s four main hospitals. This is an example of what type of sampling strategy? a. Simple random sampling b. Convenience sampling c. Purposive sampling d. Stratified random sampling ANS: D

Stratified random sampling is used when the researcher knows some of the variables in the population that are critical to achieving representativeness. Variables commonly used for stratification are age, gender, ethnicity, socioeconomic status, diagnosis, geographical region, type of institution, type of care, care provider, and site of care. The variable or variables chosen for stratification need to be correlated with the dependent variables being examined in the study. Subjects within each stratum are expected to be more similar (homogeneous) in relation to the study variables than they are to be similar to subjects in other strata or the total sample. In stratified random sampling, the subjects are randomly selected on the basis of their classification into the selected strata. DIF: Cognitive Level: Application 16. A research study examined the partying styles of students in fraternities, in sororities, living in

dorms, and living in private residences. Ten students from each group were included in the research. This is an example of which type of sampling strategy? a. Quota sampling b. Cluster sampling c. Purposive sampling d. Stratified random sampling ANS: A

Quota sampling uses a convenience sampling technique with an added feature, a strategy to ensure the inclusion of subject types or strata in a population that are likely to be underrepresented in the convenience sample, such as women, minority groups, elderly adults, poor people, rich people, and undereducated adults. This method may also be used to mimic the known characteristics of the target population or to ensure adequate numbers of subjects in each stratum for the planned statistical analyses. The technique is similar to the one used in stratified random sampling, but the initial sample is not random. DIF: Cognitive Level: Application 17. A sample is chosen for a study on average heights and weights of adult males in a major city.

The researcher uses a convenience sampling method, enacting this by going door-to-door in a neighborhood in St. Paul, Minnesota. Unbeknownst to the researcher, this neighborhood is very rich in persons of Norwegian descent, who coincidentally are the tallest Caucasians on the planet. What type of sampling error is most likely to occur due to this sampling method? a. Random variance b. Refusal rate c. Systematic bias d. Type II error

ANS: C

Systematic variation, or systematic bias, is a consequence of selecting subjects whose measurement values are different, or vary, in some specific way from the population. Because the subjects have something in common, their values tend to be similar to the values of others in the sample but different in some way from the values of the population as a whole. These values do not vary randomly around the population mean. Most of the variation from the mean is in the same direction; it is systematic. Random variation is the expected difference in values that occurs when one examines different subjects from the same sample. If the mean is used to describe the sample, the values of individuals in that sample will not all be exactly the same as the sample mean. Values of individual subjects vary from the value of the sample mean. The difference is random because the value of each subject is likely to vary in value/direction from the previously measured one. All the values in the sample may tend to be higher or lower than the mean of the population. DIF: Cognitive Level: Application 18. Choose the nonprobability sampling method. a. Cluster b. Quota c. Stratified random d. Systematic ANS: B

Four commonly implemented probability sampling designs are included in this text: simple random sampling, stratified random sampling, cluster sampling, and systematic sampling. DIF: Cognitive Level: Comprehension 19. Convenience sampling + stratification = what? a. Stratified random sampling b. Quota sampling c. Purposive sampling d. Cluster sampling ANS: B

Quota sampling uses a convenience sampling technique with an added feature, a strategy to ensure the inclusion of subject types or strata in a population that are likely to be underrepresented in the convenience sample, such as women, minority groups, elderly adults, poor people, rich people, and undereducated adults. This method may also be used to mimic the known characteristics of the target population or to ensure adequate numbers of subjects in each stratum for the planned statistical analyses. DIF: Cognitive Level: Synthesis 20. A researcher consented 75 subjects, but 15 dropped out of the study while it was still in

progress. What was the sample attrition rate? a. 10% b. 15% c. 20% d. 75%

ANS: C

Sample attrition is the withdrawal or loss of subjects from a study. Sample attrition rate is calculated by dividing the number of subjects withdrawing from a study by the sample size and multiplying the results by 100%. For example, if a study had a sample size of 160 and 40 people withdrew from the study, the attrition rate would be 25%. DIF: Cognitive Level: Application 21. A researcher consented 400 subjects, but 12 dropped out of the study before it was completed.

The rest finished the study. What was the sample retention rate? a. 30% b. 38.8% c. 3% d. 97% ANS: D

The opposite of the attrition rate is the retention rate, or the number and percentage of subjects completing the study. The retention rate is calculated by dividing the number of subjects completing the study by the initial sample size and multiplying by 100%. For example, if a study had a sample size of 160 and 40 people withdrew from the study, the retention rate would be 75%. DIF: Cognitive Level: Application 22. A researcher attempted to recruit all 150 of the patients seen in the emergency department in a

3-month period for diverticulitis, but only 120 consented to participate. What is the sample size? a. 150 b. 120 c. 30 d. 80% ANS: B

A sample size is the number of subjects or participants who actually participate in at least the first phase of a study. DIF: Cognitive Level: Application 23. A researcher attempted to recruit all 150 of the patients seen in the emergency department in a

3-month period for diverticulitis, but only 120 consented to participate. What is the refusal rate? a. 100% b. 80% c. 20% d. 0% ANS: C

A refusal rate is the number and percentage of subjects who declined to participate in the study. High refusal rates to participate in a study have been linked to individuals with serious physical and emotional illnesses, low socioeconomic status, and weak social networks. The higher the refusal rate, the less the sample is representative of the target population. The refusal rate is calculated by dividing the number of potential subjects refusing to participate by the number of potential subjects meeting sampling criteria and multiplying the results by 100%. DIF: Cognitive Level: Application 24. Using a table of random numbers, a sample of 400 subjects was selected from the list of the

license numbers of all registered nurses in the state of Michigan. Each nurse was sent a letter requesting completion of an online survey on workplace bullying. This is an example of what type of sampling method? a. Simple random sampling b. Quota sampling c. Convenience sampling d. Purposive sampling ANS: A

To achieve simple random sampling, elements are selected at random from the sampling frame. This goal can be accomplished in various ways, limited only by the imagination of the researcher. A random numbers table is effective in selecting numbered elements from a master list. Simple random sampling is a probability sampling method because every member of the population has a probability higher than zero of being selected for the sample. DIF: Cognitive Level: Application 25. When grounded theory researchers recruit subjects who can provide relevant information to

explain a cluster of interlocking ideas that is unclear to the researchers, what kind of sampling is used? a. Theoretical sampling b. Convenience sampling c. Quota sampling d. Network ANS: A

Theoretical sampling is usually applied in grounded theory research to advance the development of a selected theory throughout the research process. The researcher gathers data from any individual or group that can provide relevant data for theory generation. The data are considered relevant if they include information that generates, delimits, and saturates the theoretical codes in the study needed for theory generation. DIF: Cognitive Level: Synthesis 26. Choose the sampling design that is an example of a probability sampling method. a. Purposive b. Snowball c. Stratified random d. Quota

ANS: C

There are several types of nonprobability (nonrandom) sampling designs. Each addresses a different research need. The five nonprobability sampling designs described in this textbook are (1) convenience sampling, (2) quota sampling, (3) purposive or purposeful sampling, (4) network or snowball sampling, and (5) theoretical sampling. These sampling methods are applied in both quantitative and qualitative research. However, convenience sampling and quota sampling are applied more often in quantitative, outcomes, and mixed methods research than in qualitative studies. DIF: Cognitive Level: Comprehension 27. Why is a large refusal rate a barrier to widespread generalization? a. If a study has a refusal rate higher than 30%, it is no longer considered research. b. If researchers cannot recruit subjects into their research studies, their credibility

and ethics are under serious scrutiny. c. The actual sample is not representative of the population. It is representative only of the elements of the population that chose to participate. d. If many persons refuse to participate, they might refuse to participate in interventions that the study recommends. ANS: C

Sampling theory was developed to determine mathematically the most effective way to acquire a sample that would accurately reflect the population under study. For a sample to be representative, it must be similar to the target population in as many ways as possible. It is especially important that the sample be representative in relation to the variables being studied and to other factors that may influence the study variables. A sample must be representative of the demographic characteristics, such as age, gender, ethnicity, income, and education, which often influence study variables. The accessible population must be representative of the target population. If the accessible population is limited to a particular setting or type of setting, the individuals seeking care at that setting may be different from those who would seek care for the same problem in other settings or from individuals who self-manage their problems. Representativeness is usually evaluated by comparing the numerical values of the sample (a statistic such as the mean) with the same values from the target population. A refusal rate is the number and percentage of subjects who declined to participate in the study. The higher the refusal rate, the less the sample is representative of the target population. DIF: Cognitive Level: Synthesis MULTIPLE RESPONSE 1. The population parameter for firefighters on Long Island is 79% male. The sample statistic for

three fire stations is 73% male. Why wasn’t the sample statistic the same as the population parameter? (Select all that apply.) a. Sampling error was present. b. Random variation might have occurred. c. Systematic variation might have occurred. d. The sample was fairly small. e. The sample was not perfectly representative. f. The population parameter is inaccurate.

ANS: A, B, C, D, E

The difference between a sample statistic and a population parameter is called the sampling error. A large sampling error means that the sample is not providing a precise picture of the population; it is not representative. Sampling error is usually larger with small samples and decreases as the sample size increases. Sampling error reduces the power of a study, or the ability of the statistical analyses conducted to detect differences between groups or to describe the relationships among variables. Sampling error occurs as a result of random variation and systematic variation. DIF: Cognitive Level: Application 2. If the population is E, and assuming the researcher selects part of the population as a sample,

what could be the sample? (Select all that apply.) a. A b. B c. C d. D e. E ANS: A, B, C, D

Sampling involves selecting a group of people, events, behaviors, or other elements with which to conduct a study. A sample denotes the selected group of people or elements included in a study sample; it is a subset of the population. Every element of the sample is located within the population. In the diagram, A, B, C, and D are totally contained within E. The sampling criteria determine the target population, and the sample is selected from the accessible population within the target population. DIF: Cognitive Level: Application 3. A researcher e-mails links to an online survey about multi-tasking and overcommittedness

both on and off the job, as they relate to quality of life, to a random selection of 20,000 RNs in all 50 states; this represents about 1% of the population of RNs. The return rate on the tool is 5%. The goal of this sampling method is to obtain a representative sample. Choose the correct statement(s) relative to the sample’s representativeness. (Select all that apply.) a. Since the topic has to do with multi-tasking and overcommittedness, it is likely that the results will be skewed, since RNs who are vastly overcommitted will not complete the survey. b. The sample is automatically representative if randomly selected names were used for the survey e-mailing. c. If the e-mailed subset of the population was randomly selected and the return meets the number required by power analysis, the return is representative. d. Subjects whose perceived quality of life is either very high or very low may be more inclined to participate, since they have an interest in finding more out about this relationship. e. If the 1000 subjects who return the survey constitute an insufficient number to demonstrate statistical significance, this means that the sample was not truly representative. f. The sample is so huge, it would certainly be representative of the entire population. ANS: A, D

For a sample to be representative, it must be similar to the target population in as many ways as possible. It is especially important that the sample be representative in relation to the variables being studied and to other factors that may influence the study variables. Random sampling increases the extent to which the sample is representative of the target population. Even if the original sample is random, persons who volunteer or consent to participate in a study may differ in important ways from those who are unwilling to participate. DIF: Cognitive Level: Synthesis 4. If all of the tickets purchased in this week’s state lottery is considered the population, the five

winning tickets drawn on Saturday constitute the sample. If the lottery is not “fixed,” why is this a probability sample? (Select all that apply.) a. Because according to the laws of probability, the group of five people who won is exactly representative of all of the persons who purchased tickets. b. Because each ticket purchased has a chance of being included in the sample. c. Because the tickets drawn have a high probability of being representative of all tickets purchased. d. Because use of random sampling increases the probability that those persons whose tickets win will play the lottery again. e. Because each ticket probably has an equal chance of being included in the winning group, whether or not random sampling is used. ANS: B, C

Probability sampling methods have been developed to ensure some degree of precision in estimations of the population parameters. The term probability sampling method refers to the fact that every member (element) of the population has a probability higher than zero of being selected for the sample. Since all tickets have a greater than zero chance of winning, and since the tickets drawn have a very good probability of being representative of all tickets purchased, this is a probability sample. DIF: Cognitive Level: Synthesis 5. What would represent a hypothetical population? (Select all that apply.) a. The average population of New Jersey b. Babies born in taxicabs in New York City in the coming year c. The 45 subjects whose performance supported the study hypothesis d. The percentage of the subjects who score higher than 81 on the Test of Motor

Capability e. All of the high school students at Bountiful High School who earn their Eagle

Scout rank in the academic year 2018-2019 ANS: B, E

A hypothetical population assumes the presence of a population that cannot be defined according to sampling theory rules, which require a list of all members of the population. For example, individuals who successfully lose weight would be a hypothetical population. The number of individuals in the population, who they are, how much weight they have lost, how long they have kept the weight off, and how they achieved the weight loss are unknown. Some populations are elusive and constantly changing. For example, identifying all women in active labor in the United States, all people grieving the loss of a loved one, or all people coming into an emergency department would be impossible.

DIF: Cognitive Level: Application 6. Why are broad sampling criteria preferable for descriptive nursing studies? (Select all that

apply.) a. The accessible population is often limited in size. b. They include the sample that is the most representative of the population at that site. c. Broad sampling criteria are preferable for studies conducted in natural settings. d. Broad sampling criteria eliminate more extraneous variables than do narrow sampling criteria. e. Generalization is improved with broad sampling criteria. ANS: A, B, C, E

Broad sampling criteria ensure a large target population of heterogeneous or diverse potential subjects. A heterogeneous sample increases one’s ability to generalize the findings to the target population. In descriptive or correlational studies, the sampling criteria may be defined to ensure a heterogeneous population with a broad range of values for the variables being studied. Descriptive studies, which are non-interventional, usually are conducted with minimal control of the study design, because the purpose is to count and measure characteristics about the phenomenon of interest and the study’s variables, as they exist naturally, without researcher intervention. DIF: Cognitive Level: Synthesis 7. What are the true statements about inclusion and exclusion criteria? (Select all that apply.) a. Inclusion and exclusion criteria determine the demographics of the sample. b. Inclusion and exclusion criteria are the opposites of one another. c. Inclusion and exclusion criteria must be mutually exhaustive. d. Inclusion and exclusion criteria must be mutually exclusive. e. Inclusion and exclusion criteria must address the study purpose. ANS: A, E

A study might have inclusion or exclusion sampling criteria (or both). Inclusion sampling criteria are characteristics that a subject or element must possess to be part of the target population. Exclusion sampling criteria are characteristics that can cause a person or element to be excluded from the target population. The inclusion and exclusion sampling criteria for a study should be different and not repetitive. For example, one should not have inclusion criteria of individuals 18 years of age and older and exclusion criteria of individuals less than 18 years of age because these criteria are repetitive. DIF: Cognitive Level: Analysis 8. Large sample sizes are desirable in which types of research? (Select all that apply.) a. Correlational, using an existent database b. Grounded theory c. Phenomenology d. Pilot interventional research e. Multisite randomized clinical trials f. Survey research g. Model testing h. Case study research

ANS: A, E, F, G

Descriptive case studies tend to use small samples. Groups are not compared, and problems related to sampling error and generalization have little relevance for such studies. A small sample size may better serve the researcher who is interested in examining a situation in depth from various perspectives. Other descriptive studies, particularly studies using survey questionnaires, and correlational studies often require large samples. In the past, quasi-experimental and experimental studies often used smaller samples than descriptive and correlational studies. The sample size increases in proportion to the number of variables included in data analysis. In quantitative research, the sample size must be large enough to describe variables, identify relationships among variables, or determine differences between groups. However, in qualitative research, the focus is on the quality of information obtained from the person, situation, event, or documents sampled versus the size of the sample. The intent is an in-depth understanding of a purposefully selected sample and not the generalization of the findings from a randomly selected sample to a target population, as in quantitative and outcomes research. The number of participants in a qualitative study is adequate when saturation of information is achieved in the study area. Grounded theory and phenomenology are types of qualitative research. A pilot study is a smaller version of a proposed study conducted to develop and refine the methodology or intervention hence it uses a smaller sample size. DIF: Cognitive Level: Synthesis 9. A hospital-based nurse researcher at Hospital A conducts experimental research on a rotating

bed and its effect on prevention of pressure ulcers in hip fracture patients over 80 years of age with cognitive functional impairment. Because there are so few patients over 80 with fractured hips and cognitive functional impairment, and because the researcher anticipates problems with obtaining consent, a convenience sample is utilized and every patient who meets the criteria and consents is used in the study. The bed, although expensive, is found to be much more effective in preventing pressure ulcers in this population than is turning alone. The study is published. What are the implications of applying these findings, considering the researcher’s use of a convenience sample? (Select all that apply.) a. The findings can be applied to similar patients who come to Hospital A, with the understanding that data collection will continue and represent a second study, since the research is not yet replicated. b. The findings may be applicable to similar patients who come to Hospital B, but without replication, this use cannot be mandated in the research report. c. The rotating bed should not be used outside of Hospital A at all until a replication study is conducted. d. The study findings probably represent a Type I error. It is doubtful that use of a rotating bed could produce significant findings with a convenience sample. e. The widespread use of the rotating bed has not been supported. f. Generalization is appropriate only extremely cautiously and in the same site in which the study was conducted, with tracking of subsequent data. ANS: A, B, E, F

In convenience sampling, subjects are included in the study because they happened to be at the right place at the right time. Researchers simply enter available subjects into the study until they have reached the desired sample size. Convenience sampling, also called accidental sampling, is not considered a strong approach to sampling because it provides little opportunity to control for biases. Multiple biases may exist in convenience sampling; these biases range from minimal to serious. Additional studies with large convenience samples that have similar results would indicate the effectiveness of this intervention for practice. Studies with small convenience samples should be replicated to determine the accuracy of the findings and to increase the representation of the population studied. If findings are consistent over-replications, then generalization to a larger group is possible. DIF: Cognitive Level: Analysis 10. Why are convenience samples used so frequently in nursing research? (Select all that apply.) a. More subjects consent if they can understand the sampling method. b. Obtaining a true random sample of sufficient size may be impossible. c. There is low risk of sampling bias. d. There are limited subjects available. e. Nonrandom sampling affects only generalizability, not study integrity. ANS: B, D, E

In conducting studies in nursing and other health disciplines, limited subjects are available, and it is often impossible to obtain a random sample. Thus, most nursing studies use nonprobability sampling, especially convenience sampling, to select study samples. Researchers often include any subjects willing to participate who meet the eligibility criteria. Nonrandom sampling affects only external validity, not any other type of validity. DIF: Cognitive Level: Analysis 11. If researchers are attempting to recruit subjects who are members of a group that is not

mainstream and may be disdained, why is snowball sampling often used? (Select all that apply.) a. It is less time-consuming than other methods for hard-to-access populations. b. It produces a sample that is more representative. c. It increases recruitment success. d. It produces a more diverse sample. e. It increases generalizability. ANS: A, C

function tests that are outside the normal range”? (Select all that apply.) a. Impaired liver function may have been identified by the researcher as an extraneous variable. b. The intervention planned by the researcher could have an adverse effect on

individuals with impaired liver function. c. Liver function tests are possibly being measured in order to detect the independent variable’s effect on the dependent variable. d. The researcher is attempting to eliminate persons with all laboratory tests that are outside normal range. e. The dependent variable may be abnormally elevated in persons who do not have normal liver function. ANS: A, B, C, E

Exclusion sampling criteria are characteristics that can cause a person or element to be eliminated or excluded from the target population. The usual reasons for exclusion criteria are that they are extraneous variables and, if present, they could affect the value of the dependent variable. Other reasons might include increased risk for some groups. DIF: Cognitive Level: Synthesis 13. Performing a power analysis allows the researcher to calculate the size needed to achieve an

adequate sample. Why is it preferable to calculate this number in the design phase of a quantitative study? (Select all that apply.) a. Knowing the sample size allows the researcher to strategize how to best obtain adequate participation in the study. b. Performing a power analysis increases the research’s potential for publication. c. Conducting a power analysis decreases the chance of Type I error. d. Conducting a power analysis increases effect size. e. The institutional review paperwork must include a maximum sample size. ANS: A, E

victims of intentional burning. What sampling methods are most appropriate for this study? (Select all that apply.) a. Quota sampling b. Purposive sampling c. Cluster sampling d. Stratified random sampling e. Systematic sampling f. Snowball sampling g. Theoretical sampling ANS: B, F, G

Purposive sampling, network sampling, and theoretical sampling are more commonly applied in qualitative studies than in quantitative studies. In purposive sampling, sometimes referred to as purposeful, judgmental, or selective sampling, the researcher consciously selects certain participants, elements, events, or incidents to include in the study. In purposive sampling, qualitative researchers select information-rich cases, or those cases that can teach them a great deal about the central focus or purpose of the study. Network sampling, sometimes referred to as snowball or chain sampling, holds promise for locating samples difficult or impossible to obtain in other ways or that had not been previously identified for study. Network sampling takes advantage of social networks and the fact that friends tend to have characteristics in common. Theoretical sampling is usually applied in grounded theory research to advance the development of a selected theory throughout the research process. The researcher gathers data from any individual or group that can provide relevant data for theory generation. DIF: Cognitive Level: Application 15. Why are convenience samples used so frequently in nursing research, when a random sample

would allow for greater generalizability? (Select all that apply.) a. Convenience sampling allows researchers to select not only subsets but qualities associated with them. b. Key informants are desired. c. Random sampling is really not an issue, since little nursing research is replicated. d. Potential subjects often are reluctant to consent for in-hospital research. e. Nurses are limited to the populations they serve; many populations are small and difficult to access. ANS: D, E

Nonprobability sampling methods increase the likelihood of obtaining samples that are not representative of their target populations. In conducting studies in nursing and other health disciplines, limited subjects are available, and it is often impossible to obtain a random sample. Thus, most nursing studies use nonprobability sampling, especially convenience sampling, to select study samples. Researchers often include any subjects willing to participate who meet the eligibility criteria. Healthcare studies are usually conducted with particular types of patients experiencing varying numbers of health problems; these patients often are reluctant to participate in research. Thus, nurse researchers often find it very difficult to recruit subjects for their studies and frequently must use convenience sampling to obtain their sample. DIF: Cognitive Level: Synthesis 16. A study has a power level of 0.75. What does that mean? (Select all that apply.) a. Study interventions will be statistically significant 75% of the time. b. The study has a 75% chance of detecting differences if they exist. c. The study’s sample has a 25% attrition rate, at worst. d. There is a 25% chance of detecting a Type I error. e. There is a 25% chance that the study will fail to reveal differences that actually

exist. ANS: B, E

Power is the capacity of the study to detect differences or relationships that actually exist in the population. Expressed another way, power is the capacity to reject a null hypothesis correctly. The minimum acceptable power for a study is commonly recommended to be 0.80 (80%). DIF: Cognitive Level: Application 17. Which of the following are true statements related to determination of minimum sample size?

(Select all that apply.) a. In inferential quantitative research, power analysis drives sample size. b. In pilot research, ability to address the purpose for the pilot drives sample size. c. In descriptive research, availability of subjects drives sample size. d. In both quantitative and qualitative research, available funding drives sample size. e. In qualitative research, theoretical saturation drives sample size. ANS: A, B, C, E

The deciding factor in determining an adequate sample size for correlational, quasi-experimental, and experimental studies is power. Power is the capacity of the study to detect differences or relationships that actually exist in the population. The researcher determines the sample size needed to obtain sufficient power by performing a power analysis. The adequacy of the sample size in a study should be justified by the researchers. Sample size in both quantitative and qualitative research should be determined by the researcher’s available funding. Often the number of participants in a qualitative study is adequate when saturation of information is achieved in the study area. Saturation of data occurs when additional sampling provides no new information, only redundancy of previously collected data. A pilot study’s sample size is very small—just enough to address the reason the pilot was conducted. If few relevant studies have been conducted in the area of interest, a small pilot study can be performed, and data analysis results can be used to calculate the effect size, so that the researchers can perform an informed power analysis for the subsequent quantitative study, estimating its required sample size appropriately. DIF: Cognitive Level: Synthesis 18. Why is subject selection in survey research considered nonrandom? (Select all that apply.) a. If monetary reward is offered as an inducement, subjects may participate only to

get the reward. The sample may include fewer people who are well-off financially. b. There is no direct contact with the subjects. c. Follow-up reminders make recruitment long and drawn-out. d. Inducements are essentially manipulative; potential subjects who resent

manipulation refuse to return surveys. e. Refusal rates average 50% or more, and this makes the sample nonrepresentative. ANS: A, D, E

In conducting a survey study, the researcher may never have personal contact with the subjects. To recruit such subjects, one must rely on the use of attention-getting techniques, persuasively written material, and strategies for following up on individuals who do not respond to the initial written or e-mail communication. Because of the serious problems of low response rates with surveys, using strategies to increase the response rate is critical. In some cases, small amounts of money (one to five dollars) are enclosed with the letter, which may suggest that the recipient buy a soft drink or that the money is a small offering for completing the questionnaire. This strategy imposes some sense of obligation on the recipient but is not thought to be coercive. DIF: Cognitive Level: Comprehension 19. Inclusion criteria differ from sample characteristics. Which of the following are plausible

inclusion sampling criteria for a study conducted on an acute care ward of a major hospital? (Select all that apply.) a. Mean age 62, with range from 37 through 87 b. Twenty-four male, 12 female c. Glasgow Coma Scale of at least 14 d. Twenty-one post–hip replacement, 15 post–knee replacement e. Able to read and write English ANS: C, E

Inclusion sampling criteria are characteristics that a subject or element must possess to be part of the target population. They are like a list of what you are fishing for when you go out in a boat. Sample characteristics are a description of the subjects who participated in the study; in a nursing study, these often contain information about age, gender, diagnosis, and medical condition. They are like a list of what fish you caught on the fishing trip. DIF: Cognitive Level: Synthesis 20. Inclusion sampling criteria differ from sample characteristics. Which of the following are

sample characteristics from a study conducted in a neurosurgical critical care unit of a major hospital? (Select all that apply.) a. Mean age 62, with range from 37 through 87 b. Diagnosed with neurologic impairment due to trauma or disease c. Glasgow Coma Scale range 4 to 15 d. Twenty-one male, 19 female e. Able to speak English or Spanish ANS: A, C, D

Inclusion sampling criteria are those characteristics that a subject or element must possess to be part of the target population. DIF: Cognitive Level: Synthesis

Chapter 16: Quantitative Measurement Concepts Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A shepherd in the wilds of eastern Nevada is counting the sheep, at the end of a work day.

What is another term for what the shepherd is doing? a. Estimating random error b. Measuring c. Using an interval level of measurement d. Calculating risk ratios ANS: B

Measurement is the process of assigning numbers to objects, events, or situations in accord with some rule. The numbers assigned can indicate numerical values or categories for the objects being measured for research or practice. DIF: Cognitive Level: Application 2. What kind of reliability testing involves examining the consistency of scores between two

forms of the same measure or instrument or two observers measuring the same event? a. Equivalence reliability b. Stability reliability c. External consistency d. Internal consistency ANS: A

Equivalence reliability involves examining the consistency of scores between two forms of the same measure or instrument or two observers measuring the same event. Determining interrater reliability is important when observational measurement is used in quantitative, mixed methods, and ethnographic studies. Interrater reliability values need to be reported when observational data are collected or judgments are made by two or more data gatherers. Consequently, it is used in various types of qualitative research in which data or behaviors are coded. DIF: Cognitive Level: Analysis 3. Why would interrater reliability be measured in research? a. A verbal quantitative questionnaire is filled out. b. Behavior is observed and classified. c. Phenomenology is the research method. d. Distances are measured. ANS: B

Determining interrater reliability is important when observational measurement is used in quantitative, mixed methods, and ethnographic studies. Interrater reliability values need to be reported when observational data are collected or judgments are made by two or more data gatherers. Phenomenological research commonly utilizes unstructured interviews that are informal and conversational in nature; this approach does not lend itself to a determination of interrater reliability in the same way that a quantitative strategy does.

DIF: Cognitive Level: Analysis 4. What is the purpose of determining an instrument’s internal consistency? a. It establishes face validity. b. It demonstrates that the instrument is measuring exactly what the researcher thinks

it is measuring. c. It decreases measurement error. d. It is a way of establishing test-retest reliability. ANS: D

Tests of instrument internal consistency or homogeneity, used primarily with paper-and-pencil tests or scales, address the correlation of various items within the instrument. The original approach to determining internal consistency was split-half reliability. This strategy was a way of obtaining test-retest reliability without administering the test twice. DIF: Cognitive Level: Application 5. A new and very short survey instrument is developed. It is to be used instead of a previously

validated instrument that is very long to administer. What kind of validity concept will be used for testing this new tool? a. Divergent validity b. Convergent validity c. Discriminant analysis d. Concept validity ANS: B

In examining the construct validity of a new instrument, it is important to determine how closely an existing instrument comes to measuring the same construct as the newly developed instrument (convergent validity). Divergent validity can be examined when an instrument is available that measures the construct opposite to the construct measured by the newly developed instrument. Instruments sometimes have been developed to measure constructs closely related to the construct measured by a newly developed instrument. The researcher can strengthen the validity of the instrument by testing the extent to which the two instruments can finely discriminate between these related concepts. Testing of this discrimination involves administering the two instruments simultaneously to a sample and performing a discriminant analysis. Content validity examines the extent to which the measurement method includes all the major elements relevant to the construct being measured. DIF: Cognitive Level: Application 6. Which one of these instructions to the research subject will provide the highest possible level

of measurement? a. Indicate whether your income is above $20,000 a year or not. b. What was your income last year: 0 to $20,000; $20,000 to $60,000; $60,000 to $100,000; or more than $100,000? c. What was your total income last year, before taxes? Enter amount: _______ d. Did you earn money last year? ANS: C

An important rule of measurement is that one should use the highest level of measurement possible because it allows a wider range of statistical tests to be considered for use. For example, one can collect data on age (measured) in a variety of ways: (1) obtain the actual age of each subject (ratio level of measurement); (2) ask subjects to indicate their age by selecting from a group of categories, such as 20 to 29, 30 to 39, and so on (ordinal level of measurement); or (3) sort subjects into two categories of younger than 65 years of age and 65 years of age and older (nominal level of measurement). DIF: Cognitive Level: Application 7. A band is in on a multicity tour, and souvenir shirts are ordered from a factory. The shirts are

shipped without the size labels. The vendor must then sort them into sizes—apparently they are small, medium, large, extra-large, and extra-extra-large. What level of measurement is this? a. Nominal b. Ordinal c. Interval d. Ratio ANS: B

Nominal level of measurement is the lowest of the four measurement levels or categories. It is used when data can be organized into categories of a defined property but the categories cannot be ordered. Data that can be measured at the ordinal level can be assigned to categories of an attribute that can be ranked. Ordinal data are considered to have unequal intervals. In interval level of measurement, distances between intervals of the scale are numerically equal. Interval scales are assumed to be a continuum of values. The researcher can identify the magnitude of the attribute much more precisely. However, it is impossible to provide the absolute amount of the attribute because of the absence of a meaningful zero point on the interval scale. Ratio level of measurement is the highest form of measure and meets all the rules of the lower forms of measures. In addition, a ratio level measurement has an absolute zero point, at which a value of zero indicates the absence of the property being measured. DIF: Cognitive Level: Application 8. A secretary in a veterinarian’s office keeps track of how many animals come in for care in a

week’s time and what types of animals they are: cat, dog, horse, gerbil, duck, snake, and so forth. What level of measurement is this? a. Nominal b. Ordinal c. Interval d. Ratio ANS: A

Nominal level of measurement is the lowest of the four measurement levels or categories. It is used when data can be organized into categories of a defined property but the categories cannot be ordered. Data that can be measured at the ordinal level can be assigned to categories of an attribute that can be ranked. Ordinal data are considered to have unequal intervals. In interval level of measurement, distances between intervals of the scale are numerically equal. Interval scales are assumed to be a continuum of values. The researcher can identify the magnitude of the attribute much more precisely. However, it is impossible to provide the absolute amount of the attribute because of the absence of a meaningful zero point on the interval scale. Ratio level of measurement is the highest form of measure and meets all the rules of the lower forms of measures. In addition, a ratio level measurement has an absolute zero point, at which a value of zero indicates the absence of the property being measured. DIF: Cognitive Level: Application 9. Mark is in third grade and has just learned how to use a ruler to measure. He has become a

measuring fool. He measures everything in the house, writing down all the measurements, and gaily announcing to his mom, “Hey, Mom. Guess what? The salt shaker is four and a quarter inches tall.” What level of measurement is this? a. Nominal b. Ordinal c. Interval d. Ratio ANS: D

Nominal level of measurement is the lowest of the four measurement levels or categories. It is used when data can be organized into categories of a defined property but the categories cannot be ordered. Data that can be measured at the ordinal level can be assigned to categories of an attribute that can be ranked. Ordinal data are considered to have unequal intervals. In interval level of measurement, distances between intervals of the scale are numerically equal. Interval scales are assumed to be a continuum of values. The researcher can identify the magnitude of the attribute much more precisely. However, it is impossible to provide the absolute amount of the attribute because of the absence of a meaningful zero point on the interval scale. Ratio level of measurement is the highest form of measure and meets all the rules of the lower forms of measures. In addition, a ratio level measurement has an absolute zero point, at which a value of zero indicates the absence of the property being measured. DIF: Cognitive Level: Application 10. Depression is measured by the Beck Depression Inventory, which adds up scores from 21

items to provide a total value ranging from 0 to 63. What level of measurement is this? a. Nominal b. Ordinal c. Interval d. Ratio ANS: C

Nominal level of measurement is the lowest of the four measurement levels or categories. It is used when data can be organized into categories of a defined property but the categories cannot be ordered. Data that can be measured at the ordinal level can be assigned to categories of an attribute that can be ranked. Ordinal data are considered to have unequal intervals. In interval level of measurement, distances between intervals of the scale are numerically equal. Interval scales are assumed to be a continuum of values. The researcher can identify the magnitude of the attribute much more precisely. However, it is impossible to provide the absolute amount of the attribute because of the absence of a meaningful zero point on the interval scale. Ratio level of measurement is the highest form of measure and meets all the rules of the lower forms of measures. In addition, a ratio level measurement has an absolute zero point, at which a value of zero indicates the absence of the property being measured. DIF: Cognitive Level: Application 11. Inclusion criteria and exclusion criteria in sample selection are mutually exclusive and

mutually exhaustive. A researcher has a list of all of the study’s inclusion and exclusion criteria. These then must be sorted into an inclusion list and an exclusion list. How is this method of sorting best classified? a. Nominal b. Categorical c. Interval d. Ratio ANS: A

Nominal level of measurement is the lowest of the four measurement levels or categories. It is used when data can be organized into categories of a defined property but the categories cannot be ordered. A study might have inclusion or exclusion sampling criteria (or both). Inclusion sampling criteria are characteristics that a subject or element must possess to be part of the target population. Exclusion sampling criteria are characteristics that can cause a person or element to be eliminated or excluded from the target population. The inclusion and exclusion sampling criteria for a study should be different and not repetitive. For example, one should not have an inclusion criterion of individuals 18 years of age and older and an exclusion criterion of individuals less than 18 years of age because these criteria are repetitive. DIF: Cognitive Level: Synthesis 12. A student finds a tool that measures adaptability and wants to use it for the student’s master’s

thesis. The tool has 25 items, and they are all of the ordinal level, scaled 0 through 5. The authors of the tool, all pragmatists, are most likely to identify which level of measurement for this tool? a. Ratio level b. Interval level c. Ordinal level d. Nominal level ANS: B

Pragmatists often treat ordinal data from multi-item scales as interval data, using statistical methods (parametric analysis techniques) to analyze them, such as the Pearson product-moment correlation coefficient, t-test, and analysis of variance (ANOVA), which are traditionally reserved for interval or ratio level data. Fundamentalists insist that the analysis of ordinal data be limited to statistical procedures designed for ordinal data, such as nonparametric procedures. DIF: Cognitive Level: Analysis 13. Interval scales of measurement (IQ tests, anxiety inventories, mental status examinations) are

products of man’s invention how frequently? a. Never b. Sometimes c. Frequently d. Always ANS: D

In interval level of measurement, distances between intervals of the scale are numerically equal. Such measurements also follow the previously mentioned rules: mutually exclusive categories, exhaustive categories, and rank ordering. Interval scales are assumed to be a continuum of values. The researcher can identify the magnitude of the attribute much more precisely. However, it is impossible to provide the absolute amount of the attribute because of the absence of a zero point on the interval scale. In nursing, the characteristic we want to measure often is an abstract idea or concept, such as pain, stress, depression, anxiety, caring, or coping. An abstract concept is not measured directly; instead, indicators or attributes of the concept are used to represent the abstraction. This is referred to as indirect measurement. Multi-item scales have been developed to measure abstract concepts, such as the Spielberger State-Trait Anxiety Inventory developed to measure individuals’ innate anxiety trait and their anxiety in a specific situation. These scales have been created by humans for indirect measurement of complex concepts and are considered by most researchers to be interval-level measurement. DIF: Cognitive Level: Analysis 14. Tests of stability reliability, such as test-retest, can reveal random measurement error. Why is

systematic measurement error not revealed when stability reliability determinations are made? a. Actually, reliability testing does not reveal the type of error: differences on test-retest can indicate problems with both random and systematic measurement error. b. Tests of stability reliability are not powerful enough to pick up systematic measurement error because of its subtlety. c. If an instrument systematically measures all blood pressures 10 points high, it will do so both at baseline and on retesting. d. The direction of the systematic measurement error is reversed on retesting, so it is not visible in the statistical analysis. ANS: C

Specificity of a screening or diagnostic test is the proportion of patients without the disease who have a negative test result or true negative. A highly specific test is very useful as a screening tool when the intention is to rule out the presence of a disease that is contagious and highly desirable to treat, such as tuberculosis. DIF: Cognitive Level: Analysis 16. Which is the highest form of measurement? a. Interval b. Nominal c. Ordinal d. Ratio ANS: D

The levels of measurement, from lower to higher, are nominal, ordinal, interval, and ratio. Variables measured at the interval or ratio level can be analyzed with the most powerful statistical techniques available, which are more effective in identifying relationships among variables or determining differences between groups. DIF: Cognitive Level: Comprehension 17. A researcher is developing a tool to measure predelinquent behaviors in preadolescence. The

researcher has already reviewed the literature, gathered qualitative data from experts, pilot-tested hundreds of predelinquent preadolescents, and analyzed the findings. It is clear that the tool actually measures what it is supposed to measure. This reflects the tool’s: a. validity. b. measurement error. c. reliability. d. sensitivity. ANS: A

The validity of an instrument indicates the extent to which it actually reflects or is able to measure the construct being examined. The development of an instrument’s validity is complex, includes several validity procedures, and occurs over years of use of the instrument in studies. This process may include an extensive literature search, consultation with experts, and pilot testing. Measurement error is the difference between what exists in reality and what is measured by an instrument. Measurement error exists in both direct and indirect measures and can be random or systematic. The reliability of an instrument denotes the consistency of the measures obtained of an attribute, concept, or situation in a study or clinical practice. Reliability is concerned with the precision, reproducibility, and comparability of a measurement method. Sensitivity is the proportion of patients with the disease who have a positive test result or true positive on a screening test. DIF: Cognitive Level: Synthesis MULTIPLE RESPONSE 1. Which items are examples of indirect measurement? (Select all that apply.) a. Self-report of physical activity b. Level of consciousness c. Height d. Hope e. Depression ANS: A, D, E

An abstract concept is not measured directly; instead, indicators or attributes of the concept are used to represent the abstraction. This is referred to as indirect measurement. Common abstract concepts measured in nursing include anxiety, stress, coping, quality of life, and pain. DIF: Cognitive Level: Application 2. Which of the statements is true, relative to error? (Select all that apply.) a. True score plus error score equals observed score. b. Random error of measurement increases the mean. c. The mean of the true measurements is equal to the mean of the observed

measurements when there is no systematic error. d. No measurement of anything is ever correct. e. Measurement error always exists, if a straightforward measurement like counting

is made often enough and by enough people. ANS: A, C, E

Measurement error is the difference between what exists in reality and what is measured by an instrument. Measurement error exists in both direct and indirect measures and can be random or systematic. According to measurement theory, there are three components to a measurement score: true score, observed score, and error score. The theoretical equation of these three measures is as follows: Observed score (O) = true score (T) + random error (E). Random error does not influence the mean to be higher or lower but rather increases the amount of unexplained variance around the mean.

DIF: Cognitive Level: Analysis 3. Which statements are true, relative to systematic error? (Select all that apply.) a. If the amount of the systematic error is known, true scores can be retrieved. b. Systematic error may be decreased by proper instrument calibration. c. Systematic error results in values that vary in one direction from the true scores. d. Systematic error results from researcher fatigue or inattention. e. Systematic error changes the mean but not the relative magnitude of the variance. ANS: A, B, C, E

Measurement error that is not random is referred to as systematic error. A scale that weighs study participants 3 pounds more than their true weights is an example of systematic error. All of the body weights would be higher, and, as a result, the mean would be higher than it should be. Systematic error occurs because something else is being measured in addition to the concept. Systematic error is considered part of T (true score) and reflects the true measure of A - 1, not A. Adding the true score (with systematic error) to the random error (which is 0) yields the observed score, as shown by the following equation: T (true score with systematic error) + E (random error of 0) = O (observed score) DIF: Cognitive Level: Analysis 4. What is the true statement, related to stability reliability? (Select all that apply.) a. It is useful for establishing the validity of a physiological measure. b. It establishes the consistency of repeated measures of the same attribute with the

use of the same scale or instrument over time. c. It reveals random error but not systematic error. d. It is sometimes referred to as test-retest reliability. e. It may be difficult to interpret whether a measurement has unacceptable stability

reliability or whether maturation has affected subjects’ responses. ANS: B, C, D, E

the Spielberger State-Trait Anxiety Inventory (0 to 40 points), and systolic blood pressure readings (80 to 300 points). What are logical strategies for using these three pieces of information gathered from each subject? (Select all that apply.)

a. Add up all three numbers for a total score. b. Rank all three measures as 1—high, 2—medium, and 3—low, and sum the result. c. Determine the most accurate measurement, and give it more weight than the others

in a ranking. d. Determine the most accurate measurement in the first few subjects, and then use it

exclusively. e. Report the numbers individually without summing them. ANS: B, D, E

Another effective means of diminishing systematic error is to use more than one measure of an attribute or a concept and to compare the measures. To make this comparison, researchers use various data collection methods, such as scale, interview, and observation. Campbell and Fiske developed a technique of using more than one method to measure a concept, referred to as the multimethod-multitrait technique. These techniques allow researchers to measure more dimensions of abstract concepts, and the effect of the systematic error on the composite observed score decreases. Multimethod measurement strategies decrease systematic error by combining the values in some way to give a single observed score of anxiety for each subject. However, sometimes it may be difficult logically to justify combining scores from various measures, and a mixed methods approach might be the most appropriate to use in the study. DIF: Cognitive Level: Application 6. A researcher administers a test of hopelessness to 50 teen mothers in a continuation high

school, in order to norm it for a study planned for the subsequent semester. This norming process is part of the protocol approved by the Institutional Review Board (IRB). Retesting in 2 weeks reveals different values for many of the subjects’ paired tests. What should the researcher do now, and why? (Select all that apply.) a. Administer the test a third time and see whether there is a trend. The subjects may be becoming more/less hopeless because of an external factor or a Hawthorne effect. b. Calculate statistical tests to determine whether there are about the same amounts of positive change and negative change for the pooled sample, and whether the means are very similar for the two measurements. If so, this represents normal fluctuation of mood. c. After obtaining IRB approval for study revision, ask several of the 50 subjects with large changes about their recent experiences and discover whether there is an underlying reason for the change. d. Use the second value, not the first, for all data analysis. The subjects have evidently reexamined their feelings and discovered new insights. e. Consider the multitrait-multimethod technique for this complex concept. A single measurement doesn’t seem to be capturing the concept very well. ANS: A, B, C, E

Stability reliability is concerned with the consistency of repeated measures of the same attribute with an instrument over time. Test-retest reliability is conducted to examine instrument stability, which reflects the reproducibility of a scale’s scores on repeated administration over time when a subject’s condition has not changed. Subjects may alter their normal behaviors because they are being scrutinized. This phenomenon, known as reactivity, or the Hawthorne effect, could influence the research outcomes, threatening the validity or accuracy of the measurements. A third measurement may capture this Hawthorne effect. To capture a complex concept, researchers use the multimethod-multitrait technique, or even a mixed methods design, employing a variety of data collection methods, such as scale, interview, and observation. These techniques allow researchers to measure more dimensions of abstract concepts, and the effect of the systematic error on the composite observed score decreases. This change could be due to normal random measurement error. For example, with random error, one subject’s observed score may be higher than his or her true score, whereas another subject’s observed score may be lower than his or her true score. According to measurement theory, the sum of random errors is expected to be zero, and the random error score (E) is not expected to correlate with the true score (T). If so, the sum of the error (the measured change) for all subjects should be zero, and the means on the 2 days should be the same. Random error does not influence the mean to be higher or lower but, rather, increases the amount of unexplained variance around the mean. Many of the phenomena studied in nursing, such as hope, coping, pain, and anxiety, do change over short intervals. Thus, the assumption that if the instrument is reliable, values will not change between the two measurement periods may not be justifiable. Perhaps true change has occurred. DIF: Cognitive Level: Analysis 7. A researcher administers a 40-item instrument that measures anxiety to 30 mothers of

9-month-old triplets, repeating it in 2 weeks. Over half of the scores are higher. Why? (Select all that apply.) a. The mothers are more anxious. The babies are becoming more mobile, and the mothers’ anxiety is well founded. b. There may have been random error of measurement. The researcher should compare the group means; if they are the same, it’s only random error. c. This may represent systematic error of measurement. d. This may have poor validity for this population and concept. e. This test may have poor reliability for this population and concept. ANS: A, B, E

before children show any symptoms of the disease, because it is most curable in its early stages. The scientist wants a test that will detect all children, whether or not it produces some false positives. What does the researcher want, in terms of that new screening tool? (Select all that apply.) a. Maximum sensitivity b. A high LR+ c. Maximum specificity d. A high LRe. High interrater reliability ANS: A, D

Sensitivity is the proportion of patients with the disease who have a positive test result or true positive. A highly sensitive test is very good at identifying the patient with a disease. If a test is highly sensitive, it has a low percentage of false negatives. Specificity is the proportion of patients without the disease who have a negative test result or true negative. A highly specific test is very good at identifying patients without a disease. If a test is very specific, it has a low percentage of false positives. Likelihood ratios (LRs) are additional calculations that can help researchers to determine the accuracy of diagnostic or screening tests, which are based on the sensitivity and specificity results. LRs are calculated to determine the likelihood that a positive test result is a true positive and a negative test result is a true negative. The ratio of the true positive results to false positive results is known as the positive LR. The negative LR is the ratio of true negative results to false negative results. The very high positive LRs rule in the disease or indicate the patient has the disease. In this example, this means that positive could mean true positive or false positive and assures that very few children with leukemia will be missed. The very low negative LRs virtually rule out the chance that the patient has the disease. In this example, this means that negative means negative: if the child tests negative, leukemia is absent. DIF: Cognitive Level: Analysis

Chapter 17: Measurement Methods Used in Developing Evidence-Based Practice Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. In a study of teasing among third-graders, after an intervention on peer interactions,

behavioral observers collect the data, rating six behaviors on a 0- to 4-point scale. The observers are not trained by the same person, and there is no measure of interrater reliability. What is likely to happen? a. The variable of teasing will not be measured accurately. b. Peer interactions will not be able to be rated. c. The data will have to be scored independently by the researcher. d. Comparison with norms is unlikely. ANS: A

Observational measurement is the use of unstructured and structured inspection to gauge a study variable. The researcher must decide what he or she wants to observe, and then the researcher needs to determine how to ensure that every variable is observed in a similar manner in each instance. The researcher must create opportunities for the observational technique to be pilot-tested and to generate data on interrater reliability. DIF: Cognitive Level: Application 2. A researcher plans to conduct interviews with the first four participants in a qualitative study,

and then the researcher plans to have an assistant conduct several interviews, for the remainder of the interviews. The first thing the researcher does with the research participants is to perform a pilot interview on one participant and to have the assistant conduct a pilot interview on a different participant, and then they compare notes, discussing the process. Why is this a good idea? a. This establishes interrater reliability. b. Their styles may differ, and this way they can imitate one another’s styles. c. Pretesting of the interview protocol is essential. d. They can begin the process of data analysis at once. ANS: C

Interviews involve verbal communication during which the subject provides information to the researcher. Interviewers must be trained in the skills of interviewing, and the interview protocol must be pretested. Pilot testing allows the research team to identify problems in the design of questions, sequencing of questions, or procedure for recording responses. It also provides an opportunity to assess the reliability and validity of the interview instrument. DIF: Cognitive Level: Application 3. A researcher is interested in discovering whether the topics of written family complaints are

shared by the majority of patients’ families in a major university hospital, or whether merely a minority of the patients’ families are disgruntled. The researcher goes throughout the hospital each day and hands family members a printed form and pencil and asks them to answer the 10 questions, all of which have three to five responses, in return for a “$3 off” coupon to be used in the hospital cafeteria. What is this printed form called? a. A questionnaire

b. A Likert scale c. A forced choice scale d. An interview ANS: A

A questionnaire is a written self-report form designed to elicit information that can be obtained from a subject’s written responses. The information derived through questionnaires is similar to information obtained by interview, but the questions tend to have less depth. The Likert scale determines the opinion or attitude of a subject and contains a number of declarative statements with a scale after each statement. If the scale has an odd number of response options, then it includes a neutral or uncertain option. Use of the uncertain or neutral category is controversial because it allows the subject to avoid making a clear choice of positive or negative statements. Thus, sometimes only four or six options are offered, with the uncertain category omitted. This type of scale is referred to as a forced choice version. Interviews involve verbal communication during which the subject provides information to the researcher. DIF: Cognitive Level: Application 4. An outpatient being treated in the infusion center for thalassemia is asked to fill out a form

about satisfaction with the center, while the patient waits for the appointment. The form consists of five questions, each a statement, with six possibilities after it: Strongly Agree, Agree, Slightly Agree, Slightly Disagree, Disagree, and Strongly Disagree. What is the best description of these questions? a. A questionnaire b. A Likert scale c. A forced choice scale d. Observational checklist ANS: B

A questionnaire is a written self-report form designed to elicit information that can be obtained from a subject’s written responses. The information derived through questionnaires is similar to information obtained by interview, but the questions tend to have less depth. The Likert scale determines the opinion or attitude of a subject and contains a number of declarative statements with a scale after each statement. The Likert scale is the most commonly used of the scaling techniques in nursing and healthcare studies. Response choices in a Likert scale most commonly address agreement, evaluation, or frequency. Agreement options may include statements such as strongly disagree, disagree, uncertain, agree, and strongly agree. If the scale has an odd number of response options, then it includes a neutral or uncertain option. Use of the uncertain or neutral category is controversial because it allows the subject to avoid making a clear choice of positive or negative statements. Thus, sometimes only four or six options are offered, with the uncertain category omitted. This type of scale is referred to as a forced choice version. Observational checklists are techniques used to establish whether a behavior occurred. The observer places a tally mark on a data collection form each time he or she witnesses the behavior. DIF: Cognitive Level: Application

5. A university that is publicly funded is located in a state that is experiencing serious budget

shortfall, and the budget has been halved. The university’s 32 departments are asked to list each of their programs on an index card, resulting in 90 cards. A panel comprised of the president, provost, and five deans each independently arranges the cards into categories of 3 essential, 7 highly desirable, 15 very desirable, 40 mainstream, 15 expendable, 7 immediately expendable, and 3 targeted elimination. This is an example of which methodology? a. Delphi technique b. Rating scale c. Likert scaling d. Q-sort method ANS: D

The Delphi technique measures the judgments of a group of experts for the purpose of making decisions, assessing priorities, or making forecasts. Using this technique allows a wide variety of experts to express opinions and provide feedback, nationally and internationally, without meeting together. A rating scale is a crude form of measurement that includes a list of an ordered series of categories of a variable, which are assumed to be based on an underlying continuum. A numerical value is assigned to each category. The Likert scale determines the opinion or attitude of a subject and contains a number of declarative statements with a scale after each statement. Response choices in a Likert scale most commonly address agreement, evaluation, or frequency. Agreement options may include statements such as strongly disagree, disagree, uncertain, agree, and strongly agree. Q-sort methodology is a technique of comparative rating that preserves the subjective point of view of the individual. Cards are used to categorize the importance placed on various words or phrases in relation to the other words or phrases in the list. Each phrase is placed on a separate card. The number of cards should range from 40 to 100. The subject is instructed to sort the cards into a designated number of piles, usually 7 to 10 piles ranging from the most to the least important or from the most to least agreement. However, the subject is limited in the number of cards that may be placed in each pile. Placement of the cards fits the pattern of a normal curve. DIF: Cognitive Level: Application 6. How would a rating scale item be worded? a. “I can be alone for hours and not feel lonely”: Strongly Agree, Agree, Undecided,

Disagree, Strongly Disagree b. When I walk one block, I feel:

(1) healthy and invigorated, (2) no different from the way I ordinarily feel, (3) pleasantly tired, (4) exhausted and out of breath c. Place a vertical line intersecting this line to show what your anxiety is; the scale’s ends are 0 for “No Anxiety at All,” and 10 for “The Worst Anxiety I Have Ever Experienced.” d. Rank your supervisor’s leadership ability: Excellent, Good, Fair, Poor ANS: B

The Likert scale (A, D) determines the opinion or attitude of a subject and contains a number of declarative statements with a scale after each statement. Response choices in a Likert scale most commonly address agreement, evaluation, or frequency. Agreement options may include statements such as strongly disagree, disagree, uncertain, agree, and strongly agree. A rating scale (B) lists an ordered series of categories of a variable that are assumed to be based on an underlying continuum. A numerical value is assigned to each category, and the fineness of the distinctions between categories varies with the scale, making this one of the crudest forms of scaling technique. The visual analog scale (VAS) (c) was developed to measure magnitude, strength, and intensity of an individual’s sensations or feelings. A VAS can be administered using a drawn, printed, or computer-generated 100-mm line. The research participant is asked to place a mark through the line to indicate the intensity of the sensation or stimulus. DIF: Cognitive Level: Application 7. A Canadian researcher has had a tool published in English. The tool examines the embedded

meanings of life in a country that has colonial roots but still maintains allegiance to the mother country. There is a demand for use of the tool in French-speaking Canadian cities. Which is the type of translation that is most appropriate for this tool? a. Pragmatic translation b. Aesthetic-poetic translation c. Ethnographic translation d. Linguistic translation ANS: C

Four types of translations can be performed: pragmatic translations, aesthetic-poetic translations, ethnographic translations, and linguistic translations. Pragmatic translations communicate the content from the source language accurately in the target language. The primary concern is the information conveyed. An example of this type of translation is the use of translated instructions for assembling a computer. Aesthetic-poetic translations evoke moods, feelings, and affect in the target language that are identical to those evoked by the original material. In ethnographic translations, the purpose is to maintain meaning and cultural content. In this case, translators must be familiar with both languages and cultures. Linguistic translations strive to present grammatical forms with equivalent meanings. Translating a scale is generally done in the ethnographic mode. DIF: Cognitive Level: Application 8. A nurse believes that patient acuity is a poor measure of patient fragility. Consequently, this

nurse and another nurse construct an instrument that measures patient fragility. Of the various steps of scale testing, conceptual definition, scale construction, instrument validation, and qualitative exploration, in what order should these occur? a. Scale testing, qualitative exploration, scale construction, conceptual definition, instrument validation b. Conceptual definition, qualitative exploration, scale construction, scale testing, instrument validation c. Scale construction, conceptual definition, instrument validation, scale testing, qualitative exploration d. Instrument validation, qualitative exploration, scale construction, conceptual definition, scale testing ANS: B

In classic test theory, the following process is used to construct a scale: conceptual definition, scale design, item review, preliminary item tryouts, field testing, item analyses, selection of items to retain, conduct validity studies, reliability estimations, and compiling of scale norms. Other methods vary. However, the essential thing is to identify the concept and then proceed with design, either by quantitative or qualitative methods, following with construction, some form of testing for feasibility, and then reliability and validity determination. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. A researcher creates a new instrument to be used in a study of new graduate registered nurses’

transition to practice. The instrument contains 20 items which are statements followed by four answer options, as follows: (1) strongly disagree, (2) disagree, (3) agree, (4) strongly agree. Some of the items on the survey are worded positively (e.g., “Most days, I feel like I know what I am doing”), and some are worded negatively (e.g., “I feel bullied by my peers.”). What survey strategies are reflected in this design? (Select all that apply.) a. Counterbalancing b. Likert scale c. Visual analog scale d. Forced choice ANS: A, B, D

Response choices in a Likert scale most commonly address agreement, evaluation, or frequency. Agreement options may include statements such as strongly disagree, disagree, uncertain, agree, and strongly agree. Likert scale responses often contain four to seven options. If the scale has an odd number of response options, then it includes a neutral or uncertain option. Use of the uncertain or neutral category is controversial because it allows the subject to avoid making a clear choice of positive or negative statements. Thus, sometimes only four or six options are offered, with the uncertain category omitted. This type of scale is referred to as a forced choice version. In a Likert scale, response-set bias tends to occur when participants anticipate that either the positive or the negative (agree or disagree) response is consistently provided either in the right- or left-hand columns of the scale. Participants might note a pattern that agreeing with scale items consistently falls to the right and disagreeing to the left. Thus, they might fail to read all questions carefully and just mark the right or left column based on whether they agree or disagree with scale items. Thus, half the statements should be expressed positively and half should be expressed negatively, termed counterbalancing, to avoid inserting response-set bias into the participants’ responses. Participants would need to mark some items in the right column (agree) and others in the left column (disagree) of the scale based on their sentiments. The visual analog scale (VAS) is a magnitude scale particularly useful in scaling stimuli. Measured stimuli must be defined in a way that the subject clearly understands. Only one major cue should appear for each scale. The scale is a line 100 mm in length with right-angle stops at each end. Bipolar anchors are placed beyond each end of the line. DIF: Cognitive Level: Application 2. Which of the following are physiological measures? (Select all that apply.) a. A subject’s report of episodes of tachycardia per day b. Score on the Mini Mental Status Exam

c. Pulse rate as displayed on an ICU’s monitor d. Serum sodium e. Use of a tuning fork to measure bone conduction hearing loss ANS: A, C, D, E

research? (Select all that apply.) a. Surveys that determine the percentage of counseling appointments that have decreased psychological pain in the 72 hours following each appointment b. Photographs of chimpanzee chromosomes c. Observation ratings of the depth of a pressure ulcer d. Surgical interventions intended to ablate pain e. Opinion surveys of what patients want to have included in their discharge teaching after outpatient surgery ANS: A, E

Physiological measures include two categories, biophysical and biochemical. Biophysical measures might include the use of the stethoscope and sphygmomanometer to measure blood pressure and a biochemical measure might include the laboratory value for total cholesterol. Self-report has been used effectively to obtain physiological information and may be particularly useful when the subjects are not in closely monitored settings such as hospitals, clinics, or research facilities. For some variables, self-report may be the only means of obtaining the information. Such may be the case when study participants experience a physiological phenomenon that cannot be observed or measured by others. DIF: Cognitive Level: Application 4. Which of the following are direct measures? (Select all that apply.) a. The patient’s radial pulse rate b. The dimensions in centimeters of a decubitus ulcer c. The nurse’s observations of an infant’s apparent pain d. The physician’s measure of the patient’s deep tendon reflexes e. The patient’s estimate as to whether his lithium level is within therapeutic range f. The mother’s report of her toddler’s anxiety level before a blood draw g. The patient’s serum serotonin levels ANS: A, B, D, G

Direct measures are objective, specific measurement of a study variable. Indirect measures are often more subjective than are direct measures and may be affected by judgment or experience in administration. For example, patients might be asked to report any irregular heartbeats during waking hours over a 24-hour period (an indirect measurement of heart rhythm), or each patient’s heart could be monitored with a Holter monitor over the same 24-hour time frame (a direct measure of heart rhythm). Whenever possible, researchers usually select direct measures of study variables because of the accuracy and precision of these measurement methods. However, if a direct measurement method does not exist, an indirect measure could be used in the initial investigation of a physiological variable. DIF: Cognitive Level: Application 5. In an observational study of manifestations of various categories of sundowning behavior in

hospitalized super-elders, which of the following are true? (Select all that apply.) a. Checklists based on a rating scale would be helpful ways to records behaviors. b. Rating scales of 1—absent, 2—slight, 3—moderate, and 4—severe could be used. c. A category system should be developed before the study begins. d. The patient’s assessment of whether or not he or she is sundowning is valuable. e. There should be no overlap of the categories “confused, placid” and “confused, agitated.” f. Research assistants observing the patients should be given similar training. g. Observations should be made under similar circumstances. ANS: A, B, C, E, F, G

The first step in a structured observation is to define carefully what specific behaviors or events are to be inspected or observed in a study. From that point, researchers determine how the observations are to be made, recorded, and coded. In most cases, the research team develops an observational checklist or category system to direct collecting, organizing, and sorting of the specific behaviors or events being observed. The observational categories should be mutually exclusive. A rating scale lists an orered series of categories of a variable that are assumed to be based on an underlying continuum. A numerical value is assigned to each category; and the fineness of the distinctions between categories varies with the scale, making this one of the crudest forms of scaling technique. If the observations in a study are being conducted using multiple data collectors, it is essential that the consistency or interrater reliability of the data collectors be determined. DIF: Cognitive Level: Application 6. An outpatient’s daughter has been using a diary to track the appearance of her mother’s

decubitus ulcer when the daughter performs the daily dressing change. The patient has been newly consented for participation in the trial of a new product, presumed to accelerate healing and prevent infection. The researcher instructs the daughter in use of the new product and the use of a scale for tracking the ulcer’s healing. Scale items are change in total area (width times depth), drainage color, surrounding tissue integrity, pain, and odor. What are the advantages of using a scale instead of a diary? (Select all that apply.) a. It reduces all items to a Likert scale. b. It makes wound care easier. c. It forces a level of precision that may or may not be present in a diary. d. It produces numerical data that the researcher can easily analyze in order to provide evidence of difference between the new method and the old method.

e. It makes sure that subjects all will have daily recordings of the variables the

researcher intends to measure. ANS: C, D, E

A rating scale allows the observer to rate the behavior or event on a scale. Scales, a form of self-report, are a more precise means of measuring phenomena than questionnaires. Most scales have been developed to measure psychosocial variables. However, self-reports can be obtained on physiological variables such as pain, nausea, or functional capacity by using scaling techniques as discussed earlier in this chapter. This method provides more information for analysis than the use of dichotomous data, which indicate only that the behavior either occurred or did not occur. Scales, another form of self-reporting, are more precise in measuring phenomena than questionnaires and have been developed to measure psychosocial and physiological variables. The types of scales include the rating scale, Likert scale, and visual analog scale. DIF: Cognitive Level: Analysis 7. Choose the true statements regarding the disadvantages of observational methods. (Select all

that apply.) a. They may increase subject reactivity. b. When a single interrater is used and observations are opposite, there is no way to resolve the conflict, since each is equally correct. c. They may be used for both quantitative and qualitative research. d. They are more subjective than other types of measurements. e. They allow real-time capture of data. f. They are invariably subject to skepticism unless verified in some manner. ANS: A, D, F

Observational measurement is the use of unstructured and structured inspection to gauge a study variable. Although data collection by observation is most common in qualitative research, it is used to some extent in all types of studies. First, the researcher must decide what should be observed, and then the researcher needs to determine how to ensure that every variable is observed in a similar manner in each instance. Much attention must be given to training data collectors, especially when the observations are complex and examined over time. The researcher should create opportunities for the observation technique to be pilot-tested and to generate data on interrater reliability. Observational measurement tends to be more subjective than other types of measurement and is often seen as less credible. However, in many cases, observation is the only possible way to obtain important evidence for practice. DIF: Cognitive Level: Analysis 8. The principal disadvantages of administering open-ended questions are which of the

following? (Select all that apply.) a. They are difficult to construct. b. They are time-consuming to analyze. c. They are impractical for use with large samples. d. They cannot produce exhaustive, exclusive answers. e. They force answers. f. They can be difficult to interpret.

ANS: B, C, F

Data from open-ended questions are often difficult to interpret, and content analysis may be used to extract meaning. Open-ended questionnaire items are not advised if data are being obtained from large samples. DIF: Cognitive Level: Analysis 9. The principal advantages of using a subject’s diary either instead of interview data, or to

supplement interview data, would be which of the following? (Select all that apply.) a. Subjective perception at the time of the event is retrievable. b. Private and clandestine topics that have previously been inaccessible may be obtained through diaries. c. Diaries contain more truthful information than do other sources. d. No contact with the subject is necessary. e. Diaries may be used without consent. f. Information obtained from a diary is thought to be more accurate than that obtained from pure recall. ANS: A, B, F

A diary is a recording of events over time by an individual to document experiences, feelings, or behavior patterns. Diaries are also called logs or journals and have been used since the 1950s to collect data for research from various populations including children, patients with acute and chronic illness, pregnant women, and elderly adults. A diary, which allows recording shortly after an event, is thought to be more accurate than obtaining the information through recall during an interview. In addition, the reporting level of incidents is higher, and one tends to capture the participant’s immediate perception of situations. The diary technique gives nurse researchers a means to obtain data on topics of particular interest within nursing that have not been accessible by other means. DIF: Cognitive Level: Analysis 10. Preexistent databases used in nursing research for secondary analysis contain data of different

sorts. What are these? (Select all that apply.) a. Data collected internally by a healthcare institution for quality assurance or other review of its processes b. Data collected by unknown people for unknown reasons c. Data collected by governmental and private agencies, such as insurance companies, external to a healthcare institution d. Records locked by the courts e. Data collected by another researcher for a previous study ANS: A, C, E

Nurse researchers are increasing their use of existing databases and conducting secondary data analyses to address the research problems they have identified as relevant for practice. Health data are usually categorized into secondary data and administrative data. Secondary data are those data collected during a previous research study. Administrative data are collected within clinical agencies; obtained by national, state, and local professional organizations; and collected by federal, state, and local agencies. DIF: Cognitive Level: Analysis

11. A researcher isn’t sure whether 60-year-old women, the target population of the research, will

understand the wording of a questionnaire’s 50 items assessing knowledge of symptoms of myocardial infarction in women. Consequently, the researcher might logically decide to do which of the following? (Select all that apply.) a. Provide a small glossary defining some of the more technical terms on the questionnaire. b. Conduct a pilot of the questionnaire. c. Use a Q-sort methodology to prioritize the essential questions and decrease the questionnaire down to 20 items. d. Ask a content expert to evaluate the readability of the questionnaire. e. Arrange for several radio and TV public-service announcements, informing the public of the symptoms of myocardial infarction in women. ANS: B, D

Once the research team has satisfactorily developed the interview protocol, they must pretest or pilot-test it, using subjects similar to those who will be included in their study. Pilot testing allows the research team to identify problems in the design of questions, sequencing of questions, or procedure for recording responses. The readability level of an instrument is a critical factor when selecting an instrument for a study. Regardless of how valid and reliable the instrument is, it cannot be used effectively if study participants do not understand the items. Many word processing programs and computerized grammar checkers report the readability level of written material. Provision of a glossary is counter to the intent of the questionnaire, which is to assess knowledge of symptoms. Arranging for several radio and TV announcements will also undermine the purpose of the intent of the questionnaire. Q-sort methodology is a technique of comparative rating that preserves the subjective point of view of the individual. Using a Q-sort to decrease the number of questions will address length, not readability. DIF: Cognitive Level: Analysis 12. Which of the following constructs would be inappropriate to measure with a visual analog

scale? (Select all that apply.) a. Dichotomous variables b. Blood pressure c. Visual acuity d. Anxiety e. Playfulness ANS: A, B, C

The visual analog (sometimes spelled analogue) scale (VAS) was developed to measure magnitude, strength, and intensity of individual’s sensations or feelings. The VAS is referred to as magnitude scaling. This technique seems to provide interval-level data, and some researchers argue that it provides ratio-level data. It is particularly useful in scaling stimuli. This scaling technique has been used to measure pain, mood, anxiety, alertness, craving for cigarettes, quality of sleep, attitudes toward environmental conditions, functional abilities, and severity of clinical symptoms. The stimuli must be defined in a way that the subject clearly understands. Only one major cue should appear for each scale. The scale is a line 100 mm in length with right-angle stops at each end. Bipolar anchors are placed beyond each end of the line.

DIF: Cognitive Level: Application 13. Why is the visual analog scale (VAS) used so frequently in healthcare research? (Select all

that apply.) a. Validity is the same, regardless of how the visual analog scale is used. b. It elicits nominal-level data. c. It is easy for clients to understand. d. It is more sensitive to small changes than are numerical and rating scales. e. It requires a minimum of translation to be used in languages other than English. f. It is easy to administer and score. ANS: C, D, E, F

The visual analog scale (VAS) is a magnitude scale particularly useful in scaling stimuli. Measured stimuli must be defined in a way that the subject clearly understands. Only one major cue should appear for each scale. The scale is a line 100 mm in length with right-angle stops at each end. Bipolar anchors are placed beyond each end of the line. The VAS is frequently used in healthcare research because it is easy to construct, administer, and score. The VAS is more sensitive to small changes than numerical and rating scales and can discriminate between two dimensions of pain. Validity of the VAS has most commonly been determined by comparing VAS scores with other measures of a concept. DIF: Cognitive Level: Analysis 14. Why might a researcher use a structured interview rather than an unstructured one? (Select all

that apply.) a. The desired data for this interview are quantitative. b. Interview time is limited. c. The researcher is collecting only demographic data for the study. d. The research subjects are confused and garrulous. e. Other data were gathered previously, using an unstructured interview. ANS: A, C, E

Structured interviews are verbal interactions with subjects that allow the researcher to exercise increasing amounts of control over the content of the interview to obtain essential data for a study. The researcher designs the questions before data collection begins, and the order of the questions is specified. In some cases, the interviewer is allowed to explain the meaning of the question further or modify the way in which the question is asked so that the subject can understand it better. In more structured interviews, the interviewer is required to ask the question precisely as it has been designed. If the study participant does not understand the question, the interviewer can only repeat it. The participant may be limited to a range of responses previously developed by the researcher, similar to those in a questionnaire. If the possible responses are lengthy or complex, they may be printed on a card so study participants can review them visually before selecting a response. Qualitative research almost invariably uses interviews that are unstructured or semistructured. Unstructured interviews are informal and conversational while semistructured interviews are organized around a set of open-ended questions. Some experts call these topical or guided interviews. The degree of guidance may be as minimal as having a few initial questions or prompt or as structured as multiple predefined questions to narrow the interview to specific aspects of the phenomenon being studied. DIF: Cognitive Level: Synthesis

15. Which of the following are examples of items that could be included in a visual analog scale?

(Select all that apply.) a. Stronger than Hercules, weak as a kitten b. Passive, nonassertive c. Strongly agree, uncertain d. Stunningly beautiful, repulsively ugly e. Perfect, wrong in all respects ANS: A, D, E

The visual analog scaling technique has been used to measure pain, mood, anxiety, alertness, craving for cigarettes, quality of sleep, attitudes toward environmental conditions, functional abilities, and severity of clinical symptoms. The stimuli must be defined in a way that the subject clearly understands. The scale is a line 100 mm in length with right-angle stops at each end. Bipolar anchors are placed beyond each end of the line. These end anchors should include the entire range of sensations possible in the phenomenon being measured. Examples include “all” and “none,” “best” and “worst,” and “no pain” and “worst pain imaginable.” DIF: Cognitive Level: Application 16. A researcher plans to administer a valid research tool in another language. What must be done

in order to establish its validity in the second language? (Select all that apply.) a. Reliability testing b. Testing and then back-translating with different translators c. Analysis of values obtained with both scales d. Testing in both languages with bilingual subjects e. Concept analysis ANS: B, C, D

Translating an instrument from the original language to a target language is a complex process. One strategy for translating scales is to translate from the original language to the target language and then back-translate from the target language to the original language by using translators not involved in the original translation. Discrepancies are identified, and the procedure is repeated until troublesome problems are resolved. After this procedure, the two versions are administered to bilingual subjects and scored by standard procedures. The resulting sets of scores are examined to determine the extent to which the two versions yield similar information from the subjects. This procedure assumes that the subjects are equally skilled in both languages. DIF: Cognitive Level: Application

Chapter 18: Critical Appraisal of Nursing Studies Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A reader of qualitative research notes that a study is identified as Heideggerian

phenomenology. The purpose of the study was to explore the lived experience of the process of separating from a long-time partner and subsequently marrying another person, and to elicit descriptions of the experience’s meaning. This topic is unexplored in the literature. The sample of 21 was randomly selected from 68 volunteers. Participant interviews were tape-recorded and transcribed, and then coded by two raters, whose interrater reliability was reported as 95%. The findings revealed that there was a lengthy period of adjustment following separation, and that participants filled this time by denying permanency, creating possibilities, appreciating silence, developing personal strengths, trusting, developing skepticism, “starting a new page,” and maintaining mental boundaries. What is the most immediate evaluative critique point about this article? a. It is not clear what the findings contribute to the current body of knowledge. b. The development and implementation of the study methodology is not congruent with its philosophical foundation. c. Tape-recording, transcription, and coding by two raters are not likely to capture the essence of this experience, without video-recording and participant observation. d. The findings do not seem to be a credible reflection of reality. ANS: B

Critical appraisal of research is not complete without making judgments about the validity of the study, or in the case of qualitative studies, making judgments about the trustworthiness. The first pre-requisite for appraising qualitative studies is an appreciation for the philosophical foundation of qualitative research. Qualitative researchers design their studies to be congruent with one of a wide range of philosophies, such as phenomenology, symbolic interactionism, and hermeneutics, each of which espouses slightly different approaches to gaining new knowledge. Guided by an appreciation of qualitative philosophical perspectives, nurses appraising a qualitative study can evaluate the approach used to gather, analyze, and interpret the data. The critical appraisal of qualitative study should include a determination of whether there is methodological congruence between the philosophical tradition and qualitative approach. In the study above, parts of the development and implementation of the study (sample selection, data analysis) are not congruent with phenomenological inquiry. DIF: Cognitive Level: Comprehension 2. A nurse reader of qualitative research notes that a study is identified as grounded theory

research. The topic of study is how women leave a violent relationship. The nurse has never been in a physically abusive relationship but has, however, cared for several patients who have shared their personal stories, and the nurse has a cousin who was in a physically abusive relationship for several months. Because of this, the nurse has an immediate understanding and finds the results credible. Which is the best description of what the nurse reader has identified in the study? a. Transparency b. Resonance c. Respect

d. Transferability ANS: B

Do the findings “ring true” to the reader? This resonation, this believing on the part of the reader, in relation to something already experienced in private or professional life, supports the study’s veracity. Transparency is the extent to which the researcher provided details about the study processes such as decisions that are made during data collection and analysis, ethical concerns that were noted, and personal perspectives that may bias the findings. Appreciating philosophical perspectives and knowing qualitative approaches are superficial, without respect for the participant’s perspective. Qualitative philosophers are similar in their views of the uniqueness of the individual and the value of the individuals’ perspective. That basic valuing creates an openness to hearing a participant’s story and perceiving the person’s life, in context. This openness allows qualitative researchers and nurses using the findings to perceive different truths and to acknowledge the depth, richness, and complexity inherent in the lives of all the patients we serve. Transferability of the findings to other populations is appropriate only if the reader determines that the findings are trustworthy. DIF: Cognitive Level: Comprehension 3. What is the most accurate statement, related to study strengths? a. Study strengths always involve a level of complexity—multiple research

questions, many variables, and many references. b. Study strengths are essentially the elements of the study that the researcher

completed in accordance with the design of the study. c. The study’s strength is determined by whether the research results are statistically

significant or not. d. Strengths are determined by the number of times the article is cited by other

authors. ANS: B

The next step in critically appraising a quantitative study requires determining the strengths and limitations of the study. To determine the strengths and limitations of a study, the reader must have knowledge of what each step of the research process should be like from expert sources. The ideal ways to conduct the steps of the research process are compared with the actual study steps. One determines the extent to which the researcher followed the rules for an ideal study and identifies the study elements that are strengths or limitations. DIF: Cognitive Level: Analysis 4. In deciding whether a framework is suited to a study, what is the principal question the reader

must answer? a. Is a conceptual map provided? b. Is this the best framework for this study? c. Does the framework specify the study variables? d. Is this a theory or merely a framework? ANS: B

To critically appraise a study’s framework, the reader needs to consider the following questions: A. Is the framework explicitly expressed, or must the reviewer extract the framework from implicit statements in the introduction or literature review?

B. Is the framework based on tentative, substantive, or scientific theory? C. Does the framework identify, define, and describe the relationships among the concepts of interest? D. Is a model (diagram) of the framework provided for clarity? E. Can the study variables be linked to the relevant concepts in the model? F. How is the framework related to the body of knowledge of nursing? DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. What must the person critically appraising a qualitative research report possess as

pre-requisites, in order to begin the process? (Select all that apply.) a. Experience in performing qualitative data collection or analysis b. A respectful point of view toward the participants’ perspectives and reported experiences c. A basic knowledge of different philosophical perspectives d. The willingness to learn about the philosophical perspective supporting the study, in order to apply the standards of rigor that are consistent with that perspective e. Previous experience in critically appraising qualitative research ANS: B, C, D

Pre-requisites of philosophical foundation, type of qualitative study, and openness to study participants direct the implementation of the following guidelines for critically appraising qualitative studies. The first pre-requisite for appraising qualitative studies is an appreciation for the philosophical foundation of qualitative research. Without an appreciation for the philosophical perspective supporting the study being critically appraised, the appraiser may not appropriately apply the standards of rigor consistent with that perspective. A basic knowledge of different qualitative approaches is as essential for appraisal of qualitative studies as is knowledge of quantitative research designs is for appraising quantitative studies. Appreciating philosophical perspectives and knowing qualitative approaches are superficial, however, without respect for the participant’s perspective. Respect creates openness to knowing a participant within a naturalistic holistic framework and allows qualitative researchers and nurses using the findings to perceive different truths and to acknowledge the depth, richness, and complexity inherent in the lives of all the patients we serve. One does not need experience in performing qualitative data collection or analysis, nor does one need to have previous experience in critically appraising qualitative research in order to perform this: one must start somewhere. DIF: Cognitive Level: Analysis 2. Why is identifying the steps of the research process the first step in the critical appraisal

process for quantitative research? (Select all that apply.) a. The ability to identify the elements in the process indicates that the reader knows what these are. b. Identifying the steps is more important than understanding. c. Identifying the steps implies that the reader understands everything in the research report. d. Identifying the steps indicates that the reader comprehends the concepts in the research report.

e. Identifying the steps of the research process implies understanding the terms the

researcher uses in the research report. ANS: A, D, E

The critical appraisal process for research includes three steps: (1) identifying the steps of the research process in a study; (2) determining the study strengths and limitations; and (3) evaluating the credibility, trustworthiness, and meaning of a study to nursing knowledge and practice. These steps occur in sequence, vary in depth, and presume accomplishment of the preceding steps. However, an individual with critical appraisal experience frequently performs multiple steps of this process simultaneously. Initial attempts to comprehend research articles are often frustrating because the terminology and stylized manner of the report are unfamiliar. Identification of the steps of the research process in a quantitative study is the first step in critical appraisal. It involves understanding the terms and concepts in the report; identifying study elements; and grasping the nature, significance, and meaning of the study elements. DIF: Cognitive Level: Analysis 3. What happens during the second step of the quantitative critical appraisal process, in the case

in which the reader determines study strengths and weaknesses of a particularly weak research report? (Select all that apply.) a. The reader discovers what elements of the study are in what locations of the report. b. The reader constructs a global appraisal of the research’s lack of rigor. c. The reader’s task is to analyze the quality of the individual parts of a research report. This inevitably produces an impression not only of what the research did not do, but also what should have been done. d. The reader is required to examine each part minutely; this leads to an appreciation of what the researcher did well. e. The reader evaluates the goodness of the study. ANS: C, D

The critical appraisal process for research includes three steps: (1) identifying the steps of the research process in a study; (2) determining the study strengths and limitations; and (3) evaluating the credibility, trustworthiness, and meaning of a study to nursing knowledge and practice. Identification of the steps of the research process in a quantitative study is the first step in critical appraisal. The next step in critically appraising a quantitative study requires determining the strengths and limitations of the study. To determine the strengths and limitations of a study, the reader must have knowledge of what each step of the research process should be like from expert sources. The ideal ways to conduct the steps of the research process are compared with the actual study steps. One determines the extent to which the researcher followed the rules for an ideal study and identifies the study elements that are strengths or limitations. DIF: Cognitive Level: Analysis 4. What are the true statements related to evaluation for quantitative research appraisal? (Select

all that apply.) a. Evaluation cannot be performed without having completed the previous two steps of the appraisal process. b. Evaluation draws no conclusions about the merit of a particular research study. c. Evaluation critically analyzes the parts of a study and points out their deficits in comparison to an ideal.

d. True evaluation implies an examination of related studies, so as to assess

significance, credibility, and believability. e. Evaluation includes an assessment of the research’s contribution to nursing f.

knowledge. Evaluation plus focused literature review essentially equals concept clustering.

ANS: A, D, E, F

The critical appraisal process for research includes three steps: (1) identifying the steps of the research process in a study; (2) determining the study strengths and limitations; and (3) evaluating the credibility, trustworthiness, and meaning of a study to nursing knowledge and practice. Evaluation involves determining the credibility, trustworthiness, meaning, and usefulness of the study findings by examining the links between the study process, study findings, and previous studies. Evaluating research involves summarizing the quality of the research process and findings, determining the consistency of the findings with those from previous studies, and determining the usefulness of the findings for practice. Evaluation builds on conclusions reached during the first two stages of the critical appraisal so that the credibility, meaning, trustworthiness, and usefulness of the study findings can be determined for nursing knowledge and practice. DIF: Cognitive Level: Synthesis 5. Which of the following represent the specific attributes that qualitative research must possess

in order to be evaluated as acceptable? (Select all that apply.) a. Power analysis b. Transparency c. Instrument reliability d. Truth e. Transferability f. Transformation ANS: A, B, D, F

Critical appraisal of qualitative studies requires different detailed guidelines than those used when appraising a quantitative study; because the different qualitative approaches have different standards of quality than the quantitative standards. Transparency is the extent to which the researcher provided details about the study processes such as decisions that are made during data collection and analysis, ethical concerns that ware noted, and personal perspectives that may bias the findings. Truth as a characteristic of qualitative studies is not absolute. The evaluation is influenced by one’s confidence that the findings can be confirmed by reviewing the audit trail, field notes, or transcripts (note the overlap with transparency). Strategies implemented to increase rigor, such as comparing transcripts to audio recordings, sharing the findings with participants and writing memos, also increase one’s confidence in the truth of the findings. Truth includes the conceptual and experiential fit of the findings to your view of the phenomenon. Data analysis and interpretation transform the words of participants, the observations of the ethnographer, and the text of a document into findings. Trustworthiness is a necessary, but not sufficient, condition for transferability. Transferability is the applicability of the findings to another population or phenomenon, or stated another way the “ability to do something of value with the outcomes.” To be transferable, the findings must have meaning for similar groups or settings. Qualitative researchers who analyze the data at a superficial level will report the data as the findings, without evidence of synthesis, comparison across participants, or creation of abstract themes or categories. To transform data, the researcher must organize, interpret, compare, and re-organize phrases and themes until the meaning of the data begins to emerge. Data analysis is “the heart of qualitative inquiry.” As one might expect, for transformation of the data to occur, the researcher must spend time to become focused and immersed in the data. Immersion requires persistent engagement with the data (note overlap with time). DIF: Cognitive Level: Comprehension 6. What would be exemplified by poor “overall flow of logic in the study,” in terms of the

second step of critical appraisal? (Select all that apply.) a. The title of the study mentions “the effect of” but the study design is simple descriptive. b. There was a 60% dropout; nonetheless, the researchers claimed that the sample was representative. c. Statistical analyses used are all coherent with the variables’ levels of measurement. d. The study framework is gratuitous. It does not, in the slightest, help to explain the relationship between the principal study variables. e. The problem statement and the purpose of the study aren’t closely related. It seems like a big leap to get from the problem to the gap, and to the purpose. ANS: A, B, D, E

The reader must examine the logical links connecting one study element with another. For example, the problem needs to provide background and direction for the statement of the purpose. In addition, the reader needs to examine the overall flow of logic in the study. The variables identified in the study purpose need to be consistent with the variables identified in the research objectives, questions, or hypotheses. The variables identified in the research objectives, questions, or hypotheses need to be conceptually defined in light of the study framework. The conceptual definitions provide the basis for the development of operational definitions. The study design and analyses need to be appropriate for the investigation of the study purpose and for the specific objectives, questions, or hypotheses. Most of the limitations or weaknesses in a study result from breaks in logical reasoning.

DIF: Cognitive Level: Evaluation 7. Which of the following would be referred to as strengths in a critique of a qualitative research

report? (Select all that apply.) a. There were numerous cross-checks to ensure that what participants reported was objectively true. b. The elements of the research were present in the research report and located so that the reader could easily find them. c. The reader’s understanding of the phenomenon was better after reading the study than it had been beforehand. d. The findings were presented in a way that made sense, taken as a whole. e. The way the report was presented was congruent with its purpose, methods, and findings. f. There was a clear sense that the themes and essences emanated from the statements and perceptions of real people. ANS: B, C, D, E, F

The guidelines for determining strengths and limitations of qualitative studies include: A. Is the reader able to identify easily the elements of the research report? B. Are readers able to hear the voice of the participants and gain an understanding of the phenomenon studied? C. Does the overall presentation of the study fit its purpose, method, and findings? DIF: Cognitive Level: Analysis 8. Why is the first pre-requisite for appraising qualitative studies an appreciation for the

philosophical foundation of qualitative research? (Select all that apply.) a. Understanding the research requires a detailed understanding of each qualitative methodology. b. Qualitative research is not based on truth; it takes work for the reader to get past this stumbling block. c. There is no common ground among the qualitative methods. Each requires individual study before reading a research report can be attempted. d. All qualitative research has slightly different “ground rules.” Without an understanding of the philosophy of the method, appraisal is unfair. ANS: D

9. In which ways are critical appraisal of quantitative research and critical appraisal of

qualitative research the same? (Select all that apply.) a. Both are concerned with how well the author has established the objective truth of the data. b. Both must begin with an appreciation for the philosophical foundation of the research. c. Both define rigor in the same way. d. Both are designed to provide some evaluations about the intrinsic worth of the research. e. In both, the elements of the research report are identified. f. Both examine how well measurements in the data collection phase have maintained their precision. ANS: B, D, E

The first pre-requisite for appraising qualitative studies is an appreciation for the philosophical foundation of qualitative research. Qualitative researchers design their studies to be congruent with one of a wide range of philosophies, such as phenomenology, symbolic interactionism, and hermeneutics, each of which espouses slightly different approaches to gaining new knowledge. In quantitative research, the variables identified in the research objectives, questions, or hypotheses need to be conceptually defined in light of the study framework. Phenomenologists agree that there is no single reality. Each individual’s experience is unique and ever-changing, according to the person’s array of experiences. Reality is a subjective perception—a tenet that requires the researcher to listen, absorb, and elicit without judgment participants’ subjective experiences in as much detail as possible. Evaluations of quantitative research are concerned with whether the measurement methods are sufficiently sensitive to determine differences between subjects. Qualitative research should demonstrate attempts to confirm the accuracy of study findings through strategies such as comparing transcripts to audio recordings, sharing the findings with participants, and writing memos. Both types of critical appraisal begin with identification of the elements of the research report. DIF: Cognitive Level: Analysis

Chapter 19: Evidence Synthesis and Strategies for Implementing Evidence-Based Practice Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. Choose the most accurate statement about translational research. a. Translational research focuses on providing literal and readable translations of

research in one of the primary 15 languages in which research is read. b. Translational research is essentially evidence-based practice. c. Translational research attempts to discover something useful in basic scientific discoveries. d. Translational research is applied research based on basic research knowledge. ANS: D

Translational research is an evolving concept that is defined by the NIH as the translation of basic scientific discoveries into practical applications. Basic research discoveries from the laboratory setting need to be tested in studies with humans before application is considered. In addition, the outcomes from human clinical trials need to be adopted and maintained in clinical practice. Translational research is being encouraged by both medicine and nursing to increase the implementation of evidence-based interventions in practice and to determine if these interventions are effective in producing the outcomes desired. DIF: Cognitive Level: Analysis 2. Nursing is said to be a science and an art. If best research evidence represents the science of

nursing, what represents the art? a. Clinical expertise b. Patient values and needs c. Synthesis of best research evidence d. Eye-hand coordination ANS: A

Evidence-based practice (EBP) is the conscientious integration of best research evidence with clinical expertise and patient values and needs in the delivery of quality, cost-effective health care. Best research evidence is produced by the conduct and synthesis of a number of high-quality studies in a selected health-related area. Patient values and needs emanate from the patient. Clinical expertise provides the art of nursing practice. DIF: Cognitive Level: Comprehension 3. How is best research evidence produced? a. By the conduct and synthesis of numerous, high-quality studies in a health-related

area b. By the imaginations of creative healthcare workers, who design qualitative

research that illuminates our understanding c. By dissemination of important results at conferences d. By publications that detail the newest advances in health care ANS: A

Best research evidence is produced by the conduct and synthesis of numerous, high-quality studies in a selected health-related area. DIF: Cognitive Level: Comprehension 4. How are evidence-based practice and best research evidence related? a. With best research evidence publications, there is no evidence-based practice. b. Both evidence-based practice and best research evidence are generated by

research. c. Best research evidence is the evidence on which practice is based. d. Best research evidence includes five basic items, one of which is evidence-based

practice. ANS: C

Evidence-based practice is the conscientious integration of best research evidence with clinical expertise and patient values and needs in the delivery of quality, cost-effective health care. Best research evidence is produced by the conduct and synthesis of a number of high-quality studies in a selected health-related area. DIF: Cognitive Level: Analysis 5. If a “trigger” is defined as a condition of actual or potential harm to the patient, the nurses, or

the institution, the Iowa model becomes a reactive problem-prioritization and problem-solving process. What is its tie-in with evidence-based practice? a. The Iowa model addresses utilization of research findings at an individual level. b. Individual nurses enact an Iowa decision tree when they examine risk-management data. c. Available published evidence drives the process, as scholars review the literature and bring it forward for committee focus. d. When evidence is available, it is used for problem-solving. ANS: D

The Iowa Model of Evidence-Based Practice provides direction for the development of EBP in a clinical agency. In a healthcare agency, triggers initiate the need for change, and the focus should always be to make changes based on best research evidence. These triggers can be problem-focused and evolve from risk-management data, process improvement data, benchmarking data, financial data, and clinical problems. The triggers can also be knowledge-focused, such as new research findings, changes in national agencies or organizational standards and guidelines, an expanded philosophy of care, or questions from the institutional standards committee. The triggers are evaluated and prioritized based on the needs of the clinical agency. If a trigger is considered an agency priority, a group is formed to search for the best evidence to manage the clinical concern. In some situations, the research evidence is inadequate to make changes in practice, and additional studies are needed to strengthen the knowledge base. Sometimes the research evidence can be combined with other sources of knowledge (theories, scientific principles, expert opinion, and case reports) to provide fairly strong evidence for developing research-based protocols for practice. The strongest evidence is generated from meta-analyses of several RCTs and systematic reviews that usually include meta-analyses, and individual studies. Systematic reviews provide the best research evidence for developing evidence-based guidelines. The research-based protocols or evidence-based guidelines are pilot-tested on a particular unit and then evaluated to determine the impact on patient care. If the outcomes are favorable from the pilot test, the change is made in practice and monitored over time to determine its impact on the agency environment, staff, costs, as well as the patient and family. An agency can promote EBP by using the Iowa model to identify triggers for change, implement patient care based on the best research evidence, and monitor changes in practice to ensure quality care. DIF: Cognitive Level: Synthesis 6. In the Iowa model, what is the focus of intervention? a. The patient level b. The family level c. The institutional level d. The conceptual level ANS: C

cognitive-behavioral strategy for decreasing pain—hypnosis, distraction, focusing, music therapy, and so forth. Why would these 12 studies make a poor meta-analysis? a. Cognitive-behavioral interventions are not a suitable focus for all patients and,

consequently, should not be studied. b. Twelve studies would be too many for synthesis of any kind. c. Secondary analyses of pooled data are not used for meta-analysis on pain, because of interindividual differences in perception. d. The result, if statistically significant, will produce a general recommendation, “If in pain, do something cognitive-behavioral,” which is meaningless. ANS: D

A meta-analysis is a research synthesis strategy that involves statistically pooling the sample and results from previous studies with the same research design. Meta-analyses provide one of the highest levels of evidence about the effectiveness of an intervention. This approach has objectivity because it includes analysis techniques to determine the effect of an intervention while examining the influences of variations in the studies selected for the meta-analysis. The studies to be included in the analysis must be examined for variations or heterogeneity in such areas as sample characteristics, sample size, design, types of interventions, and outcomes variables and measurement methods. Heterogeneity in the studies to be included in a meta-analysis can lead to different types of biases, which could produce broad and meaningless results. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. The Magnet Recognition Program represents a credentialing process, whereby organizations

of quality are recognized. What does the Magnet Recognition Program require, relative to research and evidence-based practice (EBP)? (Select all that apply.) a. Nurses will participate in the institutional review process. b. Nursing research will be a budget line item. c. Only nurse researchers will conduct clinical research. d. The institution will keep track of nursing research projects in progress and recently completed. e. Care applied to patients will be, in a large part, supported by research. ANS: A, B, D

Approval for Magnet status is obtained through the American Nurses Credentialing Center (ANCC). The Magnet Recognition Program recognizes EBP as a way to improve the quality of patient care and revitalize the nursing environment. Magnet status requires that healthcare agencies promote the following research activities: reading and using research evidence in practice, budgeting for research activities, providing a research infrastructure with the help of consultants, conducting research and mentoring nursing staff in research activities, developing policies for protection of subjects’ rights, and documenting internal and external research activities. Important research outcomes documented in a Magnet application include nursing studies conducted, professional publications, and research presentations. Documentation of a study in a Magnet report must include the following: study title, principal investigator or investigators, role of nurses in the study, and study status. DIF: Cognitive Level: Analysis 2. Evidence-based practice is based on three things. On what would a nurse base practice in a

new area of nursing, if there is yet no research evidence? (Select all that apply.)

a. b. c. d. e.

Nursing theory The nurse’s own clinical expertise Client values and needs Evidence in parallel, related fields Past documentation in the medical record

ANS: B, C, D

Evidence-based practice is the conscientious integration of best research evidence with clinical expertise and patient values and needs in the delivery of quality, cost-effective health care. Best research evidence is produced by the conduct and synthesis of a number of high-quality studies in a selected health-related area. DIF: Cognitive Level: Analysis 3. Which of the following statements about the Stetler model of research utilization are true?

(Select all that apply.) a. Its goal is to assure that research is utilized. b. It is a framework. c. It facilitates synthesis of research knowledge. d. It is used to update hospital policies. e. In its validation phase, scientific soundness is assessed. f. It provides a step-by-step way to assess and evaluate research findings. ANS: B, C, D, E, F

The Stetler (2010) model provides a comprehensive framework to enhance the use of research evidence by nurses to facilitate evidence-based practice. The research evidence can be used at the institutional or individual level. At the institutional level, synthesized research knowledge is used to develop or update protocols, algorithms, policies, procedures, or other formal programs implemented in the institution. Individual nurses, including practitioners, educators, and policymakers, summarize research and use the knowledge to influence educational programs, make practice decisions, and impact political decision-making. The five phases of the Stetler model are: (1) preparation, (2) validation, (3) comparative evaluation and decision making, (4) translation and application, and (5) evaluation. In the validation phase, research reports are critically appraised to determine their scientific soundness. DIF: Cognitive Level: Analysis 4. What are the basic problems with meta-syntheses of qualitative research? (Select all that

apply.) a. Qualitative research itself is a subjective interpretation; a meta-synthesis of qualitative research is a compiling of information generated subjectively. b. If individual studies have different methods, it may be difficult to find common ground and to devise a meaningful interpretation of the results. c. Qualitative research has no implications for practice, so performing a meta-synthesis is unjustifiable. d. In qualitative research, multiple valid interpretations may occur if different researchers examine the text. e. The recommendation for practice that results from meta-synthesis of qualitative research lacks statistics. f. The raw data are not available to the qualitative meta-synthesizer.

ANS: A, B, D, F

Meta-synthesis is defined as the systematic compiling and integration of qualitative study results to expand understanding and develop a unique interpretation of study findings in a selected area. The focus is on interpretation rather than the combining of study results as with quantitative research synthesis. Meta-synthesis involves the breaking down of findings from different studies to discover essential features and then the combining of these ideas into a unique, transformed whole. Sandelowski and Barroso identified meta-summary as a step in conducting meta-synthesis. The process of interpretation occurs in the mind of the researcher. Corbin and Strauss describe interpretation as translating the words and actions of participants into meanings that readers and consumers can understand. The virtual text grows in size and complexity as the researcher reads and rereads the transcripts. Throughout the process of analysis, the virtual text develops and evolves. Although multiple valid interpretations may occur if different researchers examine the text, all findings must remain trustworthy to the data. This trustworthiness applies to the unspoken meanings emerging from the totality of the data, not just the written words of the text. DIF: Cognitive Level: Synthesis 5. The Grove Model for Implementing Evidence-Based Guidelines in Practice includes which of

the following steps? (Select all that apply.) a. b. c. d. e.

Identifying a practice problem Searching for the best research evidence to manage the problem Asking a research question Identifying an evidence-based guidelines Designing an original research study to answer the research question

ANS: A, C, D

In the Grove Model for Implementing Evidence-Based Guidelines in Practice, nurses identify a practice problem, search for the best research evidence to manage the problem in their practice, and identify an evidence-based guideline. The model does not involve asking a research question or designing original research. DIF: Cognitive Level: Comprehension 6. A systematic review should address the components specified in PICOS. Why is this so?

(Select all that apply.) a. Interventional research always uses some means of comparison. b. “Interventions” that are actually naturally occurring conditions should be noted, since they decrease confirmatory power of the collective evidence. c. Study design is essential, since recommendations for change in practice can be based only on some designs. d. Desired outcomes, not actual outcomes of the study, are the focus of the review. e. The specific population from which a sample was drawn, and its similarity to those of others studies reviewed, affects generalizability. ANS: A, B, C, E

A systematic review is a structured, comprehensive synthesis of the research literature to determine the best research evidence available for addressing a healthcare question. A systematic review involves identifying, locating, appraising, and synthesizing quality research evidence for expert clinicians to use to promote an EBP. Systematic reviews are often conducted by two or more researchers and/or clinicians in a selected area of interest to determine the best research knowledge in that area. Systematic reviews must be conducted with rigorous research methodology to promote the accuracy of the findings and minimize the reviewers’ bias. A systematic review or meta-analysis includes an introduction that provides a background of what is known and not known in a selected area with a rationale for conducting the review. A relevant clinical question is developed to focus the review process. One of the most common formats used to develop a relevant clinical question to guide a systematic review is the PICO or PICOS format described in the Cochrane Handbook for Systematic Reviews of Interventions. PICOS format includes the following elements: P—population or participants of interest; I—intervention needed for practice; C—comparisons of the intervention with control, placebo, standard care, variations of the intervention, or different therapies; O—outcomes needed for practice; and S—study design. Quality interventional-designed studies such as RCTs, experimental studies, and quasi-experimental studies are needed to generate sound evidence for practice. DIF: Cognitive Level: Synthesis

Chapter 20: Collecting and Managing Data Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. Planning as a step in the quantitative research process ends when the data collection has

begun. Which is the true statement about planning in the qualitative research process? a. Since sample size is not usually decided upon ahead of time, there is no practical reward to planning the qualitative research study ahead of time. b. There is no planning in the qualitative research process; it all emanates from the data collected. c. Everything about a qualitative study is planned ahead of time, except for analysis of the data. d. The researcher may adapt strategies for data collection or analysis well into the study. ANS: D

Factors of cost, time, availability of assistance, and need for consistency shape the development of the data collection plan, detailing the study that will be implemented. The plan for collecting data is specific to the study being conducted, beginning with recruitment. This extensive planning increases accuracy of the data collected and validity of the study findings. In qualitative methods, however, the researcher may adapt the data collection or analysis strategies during the study. DIF: Cognitive Level: Analysis 2. What is the general rule about collecting demographic data during an interview? a. The mood of the qualitative interview, so crucial to quality data capture, may be

intruded upon by demographic data collection. b. In quantitative interviews, everything excerpted from medical records must again

be verified in face interviews. c. In qualitative interviews, routinely asking 20 or 30 demographic questions sets the stage for actual data collection. d. If data can be obtained in other ways, it is best to leave the valuable interview time for actual interviewing. ANS: D

The researcher should consider the importance of each piece of data and the subject’s time required to collect it. If the data can be obtained from patient records or any other written sources, researchers do not need to ask the subject to provide this information again. To collect data from a patient’s records, the researcher must make sure to include permission to do this in the consent form and ensure that the institutional review board has authorized the team to do this. The qualitative researcher has the power to shape the interview agenda. Participants have the power to choose the level of responses they will provide. The researcher might begin the interview with a broad request such as “Describe for me your experience with . . . .” or “Tell me about . . . .” Ideally, the participant will respond as though she or he is telling a story. The researcher responds nonverbally with a nod or eye contact to convey interest in what is being said and tries to avoid agreeing or disagreeing with what the participant is saying. The less the researcher says, the better.

DIF: Cognitive Level: Comprehension 3. A researcher is collecting data in a hospital during cardiopulmonary resuscitation (CPR). The

researcher has devised a data collection form that contains five columns for data entry. During the first three data collection periods, the form works reasonably well, although the researcher has to turn the page over and write on the back. During the fourth, however, the CPR incident occurs in the Emergency Department and includes many procedures and interventions, and the researcher ends up taking a blank piece of paper and recording data on that. Later, it takes the researcher 40 minutes to unscramble and collate the data, and record it properly. What must be done now? a. The researcher will go back to the institutional review board and request permission to use a different form. b. The researcher will design a new form, with the assumption that the next CPR incident will be just as complex as the last. c. The researcher will continue to use the old form, writing on the back when necessary, and pulling out blank pieces of paper, from time to time, for additional data recording. d. The researcher will decrease the amount of data necessary to record by revising the old study protocol, so that fewer research questions are asked. ANS: B

Little has been written about the problems encountered by nurse researchers. Research reports often read as though everything went smoothly. Research journals generally do not provide enough space for researchers to describe the problems encountered, and inexperienced researchers may receive a rosier impression than is realistic. Some problems are hinted at in a published paper in either the limitations section or in a discussion of areas for subsequent research. A more realistic sense of problems encountered by a researcher can be obtained through personal discussions with the primary author about the process of data collection for a particular sample, or the use of a particular method or instrument. Even following a pilot study, researchers may encounter challenges during the data collection process. Sometimes changes must be made in the way the data are collected, in the specific data collected, or in the timing of data collection. Potential subjects, as well as healthcare workers in a given area, react to a research study in unpredictable ways. Institutional changes may force modifications in the research plan, or unusual or unexpected events may occur. Data collection processes must be as consistent as possible, but flexibility is also needed in dealing with unforeseen problems. Sometimes, sticking with the original plan no matter what happens is a mistake. Skills in finding ways to resolve problems that protect the integrity of the study are critical. Data collection forms themselves do not need institutional review board (IRB) approval—the information to be collected is what the IRB approves. DIF: Cognitive Level: Application 4. The quantitative researcher collects many pieces of quantitative data as words, not numbers.

Prior to statistical analysis, all of the data pieces must be coded. What does this mean? a. The data are transformed into numerals corresponding to words, such as: 0—no college degree, 1—bachelor’s degree, 2—master’s degree, 3—PhD or EdD. b. The essence of each word is noted; later, these essences emerge as themes. c. The data are typed into a computer, and the computer is instructed to transform the words into binary values, using only 0 and 1, by adding up the numbers of each

letter in the alphabet. d. The data regarding protected data are transformed to code names; a list is made and kept in a secure location. ANS: A

If data are collected electronically, data collection and entry are simultaneous. While setting up an online instrument to be completed by subjects, the researcher will indicate the number or variable name and the code for each response for each variable (1 = Strongly disagree, 2 = Disagree, 3 = Neutral, 4 = Agree, 5 = Strongly Agree). If the researcher plans inferential statistical analysis involving age, the question needs to be open-ended to elicit the number of years. However, if the researcher asks the question with a list of options from which the subject selects (18 to 24 years, 25 to 32 years, so forth), the data will be ordinal and not suitable for inferential analysis. Categorical data are assigned a number. For example, for gender, male would be coded as “1,” female as “2,” and other as “3.” The value of the number (lower or higher) does not mean a greater or smaller quantity in this case because measurement is at the nominal level: the number represents a name, not a numerical value. The assigned number allows the data analysis program to count the frequency and percentage of each numbered category. Another common example is an item on a questionnaire about medical diagnoses or surgical procedures. Because multiple responses may need to be marked, each response is treated as a Yes/No question and coded as “1” or “0.” DIF: Cognitive Level: Application 5. A nurse is conducting her master’s thesis research in the unit in which she works as a staff

nurse. The focus of her thesis is burned children’s pain, with a child life specialist assisting the child versus without. She is providing child life specialist presence every other day at the mid-morning dressing change. For obvious reasons, she wants to keep everything else consistent for the 4 contiguous days of data collection. On the second day of four, with the child life specialist present, one child demonstrates poor pain control. The nurse researcher would ordinarily advocate for more pain medication for this child, but if she does, she will not be able to compare the data with that of the previous day. What is this an example of? a. Serendipity b. Subject as object c. Role conflict d. Passive resistance ANS: C

As a researcher, one is observing and recording events. Nurses who conduct clinical research often experience a conflict between their researcher role and their clinician role during data collection. In some cases, the researcher’s involvement in the event, such as providing physical or emotional care to a patient during data collection, could alter the event and bias the results. It would be difficult to generalize study findings to other situations in which the researcher was not present to intervene. However, the needs of patients must take precedence over the needs of the study. Serendipity is the accidental discovery of something useful or valuable that is not the primary focus of the inquiry. When researchers are under pressure to complete a study, people can be treated as objects rather than as subjects, particularly if electronic data collection is used. In addition to being unethical, such impersonal treatment alters interactions, diminishes subject satisfaction, and increases likelihood for missing data and subject attrition. Passive resistance may occur if healthcare professionals and institutional staff members working with study participants in clinical settings affect the data collection process. Some professionals may verbalize strong support for the study and yet passively interfere with data collection. For example, nurses providing care may fail to follow guidelines agreed upon for providing specific care activities being studied, or they may forget to include information needed for the study in the patient records. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. A researcher intends to collect data, including patients’ ratings of pain and anxiety, during a

procedure. No electrical equipment or photography may be used in the procedure room. In order to record the various pain and anxiety ratings, the researcher may plan to use which of the following? (Select all that apply.) a. A plug-in word processor b. A form with large margins, or a column for comments, or both c. A pencil with an eraser d. A form with prelabeled columns and rows e. A cell phone with camera ANS: B, C, D

For quantitative research, preparation begins with clarifying exactly which data will be collected, how they will be collected, and how they will be recorded. The data to be collected are determined by the variables’ operational definitions. Data collection forms must be designed so that the data are easily recorded. Pencil and paper are ideal, since they allow for erasure, in case the subject clarifies data. DIF: Cognitive Level: Application 2. Part of a research study entails that research subjects complete a printed form with

checkboxes. The researcher decides ahead of time that any item that has more than one response checked will be treated as unanswered. What are logical ways the researcher can maximize properly answered items, without skewing the data? (Select all that apply.) a. Make a rule that if there are two checked replies, only the first one will be counted. b. When the researcher hands the form to the subjects, the researcher should specify “One answer and one answer only for each of these items, please, or I won’t be able to include the double-answered ones in my report.” c. Glance at the forms as they are about to be handed in, and if two boxes for an item

are checked, ask the subject to address this. d. In the printed instructions at the top of the form, be sure to state that if a question has more than one response checked, that item will be treated as unanswered. e. Eliminate from the entire study any subject who double-selects an item. ANS: B, C, D

Decision rules for data entry should be finalized during piloting. For example, if a subject selects two responses for a single-response item, two decisions are possible: (1) the variable can be coded as missing and (2) either the higher or the lower variable can become the default value. In the latter instance, a multiple-choice question indicating how many months have elapsed since a subject visited a dentist might be answered both “six to eleven months ago” and “twelve to seventeen months ago.” The researcher, in this instance, would use “six to eleven months ago” as the default value, since the meaning of the question is not “how long has it been since you saw a dentist?” but, rather, how long has it been since you last saw a dentist?” If feasible, this particular question should then be reworded for the actual study as “When was your last visit to a dentist?” This strategy would not be feasible for all surveys, however, and depends on the wording of the item. DIF: Cognitive Level: Application 3. A researcher is studying the way that ICU nurses prioritize the charting responsibilities for

their 12-hour shift. The researcher happens to discover that nurses are administering medications as close to the ordered times as possible but consistently charting the times at which medications are ordered, not the time they are actually administered, even though that may be 2 or 3 hours later. What could the researcher do with this information? (Select all that apply.) a. The researcher could make the nurse manager aware of the finding, after the study data have all been collected, because this is essentially a medication charting error. b. Nothing. This is not a focus of the study, and the information must be suppressed. c. The researcher should take time to educate individual nurses, so that they understand that what they are doing is not honest. d. The researcher should include the findings in the article, stating that this is a time-saving strategy, since the computer allows charting of meds when ordered (instead of when administered) as a block, saving time. e. The researcher should report this information under Serendipitous Discoveries, in the article that results from the study. ANS: A, D, E

Serendipity is the accidental discovery of something useful or valuable that is not the primary focus of the inquiry. During the data collection phase of studies, researchers often become aware of elements or relationships that they had not previously identified. These aspects may be closely related to the study being conducted or have little connection with it. They come from increased awareness and close observation of the study situation. Serendipitous findings are important to the development of new insights in nursing theory. They can be important for understanding the totality of the phenomenon being examined. Educating individual nurses is sure to alienate staff. The manager is the logical choice for a person in whom to confide this information. Obviously, this should be communicated as, “Some nurses ….” rather than naming names, since the nurses’ privacy would be violated by telling their names. DIF: Cognitive Level: Application

4. How may research data, code-named and stripped of all identifiers, be stored? (Select all that

apply.) a. Separate from the master list of identifiers and codes b. Only in a locked box in a safe c. Anywhere the researcher decides to store it that has reasonable security d. Only in the original database from which it was derived e. Only in a password-protected computer, located in a private office or residence ANS: A, D

In this time of electronic storage devices and cloud storage, it is relatively easy to store data. The original data forms and database must be stored for a specified number of years dictated by the institutional review board, funding source or by the journal publisher. There are several reasons to store data. The data can be used for secondary analyses. For example, researchers participating in a project related to a particular research focus may pool data from various studies for access by all members of the group. Data should be available to document the validity of the analyses and the published results of the study. Because of nationally publicized incidents of scientific misconduct, in which researchers fabricated data and published multiple manuscripts, researchers would be wise to preserve documentation supporting the appropriate and accurate collection of data. Issues that have been raised include how long data should be stored, the need for institutional policy regarding data storage, and whether graduate students who conduct a study should leave a copy of their raw data with the university, should access to it become necessary after they leave the institution. Some researchers store their data for 5 years after publication, whereas others store their data until they retire from a research career. Researchers should check with their funding sponsors and publishers for guidelines on how long to keep the data. Most researchers store data in their offices or laboratories; others archive their data in central locations with storage fees or retrieval fees. DIF: Cognitive Level: Analysis 5. How may raw research data, with identifiers, obtained from a hospital be stored? (Select all

that apply.) a. It must be kept only in the hospital’s computer system; at the end of the workday, all excerpted data must be deleted. b. In a locked box in a safe c. In any e-mail account d. On a private website e. In a password-protected computer, located in a private office or residence ANS: B, E

In this time of electronic storage devices and cloud storage, it is relatively easy to store data. The original data forms and database must be stored for a specified number of years dictated by the institutional review board, funding source, or by the journal publisher. There are several reasons to store data. The data can be used for secondary analyses. For example, researchers participating in a project related to a particular research focus may pool data from various studies for access by all members of the group. Data should be available to document the validity of the analyses and the published results of the study. Because of nationally publicized incidents of scientific misconduct, in which researchers fabricated data and published multiple manuscripts, researchers would be wise to preserve documentation supporting the appropriate and accurate collection of data. Issues that have been raised include how long data should be stored, the need for institutional policy regarding data storage, and whether graduate students who conduct a study should leave a copy of their raw data with the university, should access to it become necessary after they leave the institution. Some researchers store their data for 5 years after publication, whereas others store their data until they retire from a research career. Researchers should check with their funding sponsors and publishers for guidelines on how long to keep the data. Most researchers store data in their offices or laboratories; others archive their data in central locations with storage fees or retrieval fees. DIF: Cognitive Level: Analysis 6. What are the purposes of completing a pilot study? (Select all that apply.) a. It provides nominal and ordinal data with which the researcher can construct better

instruments. b. It helps identify problems the researcher might encounter while collecting data. c. It justifies the existence of a research gap. d. It gives the researcher preliminary data to present the institutional review board in

order to obtain permission to conduct research. e. It provides an idea of the time lines of the proposed study, including

instrument-completion and subject recruitment. ANS: B, E

Completing a pilot is an essential step that saves difficulty later when the final steps of the research process are implemented. The aims of a pilot test may include identifying problems that may interfere with study validity or challenges in using the instruments. If the purpose is to try out the procedures, the researcher should recruit three to five subjects who meet the eligibility criteria. The same study data collection methods should be used, paying attention to how long it takes to recruit a subject, obtain informed consent, and collect all data. At the conclusion of data collection, the researcher should ask the participant to identify questions or aspects of the process that were unclear or confusing. Based on the pilot study and feedback of the first subjects, researchers may choose to modify data collection forms and methods of data collection to ensure the feasibility, validity, and reliability of the study. DIF: Cognitive Level: Analysis 7. What are the principal tasks of data collection? (Select all that apply.) a. Performing constant comparison for qualitative data b. Maintaining research controls as indicated in the study design c. Solving problems that threaten to disrupt the study d. Cross-checking with the literature review

e. Collecting data in a consistent way f. Obtaining institutional review board permission g. Selecting subjects ANS: B, C, E, G

Data collection is the process of selecting subjects and gathering data from them. The actual steps of collecting data are specific to each study and depend on both research design and measurement methods. Data may be collected on subjects by observing, testing, measuring, questioning, recording, or any combination of these methods, either conducted by the research team or retrieved from data sources. The researcher is actively involved in this process either by collecting data or by supervising data collectors. Obtaining permission occurs before data collection. DIF: Cognitive Level: Comprehension

Chapter 21: Introduction to Statistical Analysis Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A researcher who has conducted experimental research finds that in the researcher’s

145-person hospital study, the patients who are ambulated on the evening of abdominal surgery are less likely than the control group to develop postoperative pneumonia. What does the researcher infer? a. The control group resembled the experimental group in all important characteristics. b. Early ambulation and pneumonia are strongly related. c. Evening-of-surgery ambulation will prevent some cases of postoperative pneumonia in abdominal surgery patients. d. Careful support of the abdomen is important for postoperative ambulation in patients who have had abdominal surgery. ANS: C

Statisticians use the terms inference or infer in a similar way that a researcher uses the term generalize. Inference requires the use of inductive reasoning. One infers from a specific case to a general truth, from a part to the whole, from the concrete to the abstract, from the known to the unknown. When using inferential reasoning, one can never prove things; one can never be certain. However, one of the reasons for the rules that have been established with regard to statistical procedures is to increase the probability that inferences are accurate. Inferences are made cautiously and with great care. Researchers use inferences to infer from the sample in their study to the larger population. DIF: Cognitive Level: Analysis 2. In the illustration, what is this particular distribution called?

a. b. c. d.

Bimodal Normal Camelesque Negatively skewed

ANS: A

One characteristic of distributions is their modality. Most curves found in practice are unimodal, which means that they have one mode, and frequencies progressively decline as they move away from the mode. Symmetrical distributions are usually unimodal. However, curves can also be bimodal or multimodal. DIF: Cognitive Level: Application 3. A researcher reports that the heights of men aged 53 living in Rapid City, South Dakota, is

between 5'7" and 6'0" and that the confidence interval is calculated at the p < 0.05 level. What does this mean? a. If the heights of men in Rapid City, South Dakota, do not fall within the

confidence interval at least 5% of the time, a Type I error has occurred. b. If a 53-yr-old man in Rapid City, South Dakota, is measured, there is a 95% chance that his height will fall in the 5'7" through 6'0" interval. c. Ninety-five percent of the 53-year-old men living in Rapid City, South Dakota, are between 5'7" and 6'0". d. The heights of the men in the sample were all between 5'7" and 6'0", and the sample was representative of 95% of the men in town. ANS: B

When the probability of including the value of the parameter within the interval estimate is known, this is referred to as a confidence interval. Calculating a confidence interval involves the use of two formulas to identify the upper and lower ends of the interval. A confidence interval is actually an estimate. DIF: Cognitive Level: Synthesis 4. There are four data sets:

A: 1, 1, 1, 1, 1, 10, 10, 10, 10 B: 2, 2, 2, 2, 4, 8, 8, 8, 9 C: 3, 4, 4, 5, 5, 5, 6, 6, 7 D: 1, 2, 3, 4, 5, 6, 7, 8, 9 What is the mean of the four individual data sets? a. 5, 5, 5, 5 b. 1, 4, 5, 5 c. 1, 2, 5, 5 d. 5 ANS: A

The measures of central tendency are descriptive statistics. The statistics that represent measures of central tendency are the mean, median, and mode. All of these statistics are representations or descriptions of the center or middle of a frequency distribution. The mean is the arithmetic average of all of the values of a variable. The median is the exact middle value (or the average of the middle two values if there is an even number of observations). The mode is the most commonly occurring value in a data set. In a normal curve, the mean, median, and mode are equal or approximately equal. DIF: Cognitive Level: Analysis 5. There are four data sets:

A: 1, 1, 1, 1, 1, 10, 10, 10, 10 B: 2, 2, 2, 2, 4, 8, 8, 8, 9 C: 3, 4, 4, 5, 5, 5, 6, 6, 7 D: 1, 2, 3, 4, 5, 6, 7, 8, 9 What is the median of the four individual data sets? a. 5, 5, 5, 5 b. 1, 4, 5, 5 c. 1, 2, 5, 5 d. 5 ANS: B

A: 1, 1, 1, 1, 1, 10, 10, 10, 10 B: 2, 2, 2, 2, 4, 8, 8, 8, 9 C: 3, 4, 4, 5, 5, 5, 6, 6, 7 D: 1, 2, 3, 4, 5, 6, 7, 8, 9 What is the mode of the four individual data sets? a. 5, 5, 5, 5 b. 1, 4, 5, 5 c. 1, 2, 5, none d. 1 ANS: C

a. b. c. d.

1, 1, 1, 1, 1, 10, 10, 10, 10 2, 2, 2, 2, 4, 8, 8, 8, 9 3, 4, 4, 5, 5, 5, 6, 6, 7 1, 2, 3, 4, 5, 6, 7, 8, 9

ANS: C

38%; 70 students scored below the mean, but 3 scored more than 96%. This would represent what type of distribution? a. Normal b. Positively skewed c. Negatively skewed d. Leptokurtic ANS: B

Any curve that is not symmetrical is referred to as skewed or asymmetrical. Skewness may be exhibited in the curve in various ways. A curve may be positively skewed, which means that the largest portion of data is below the mean. A curve can also be negatively skewed, which means that the largest portion of data is above the mean. Few samples are perfectly symmetrical; however, as the deviation from symmetry increases, the seriousness of the impact on statistical analysis increases. In a positively skewed distribution, the mean is greater than the median, which is greater than the mode. In a negatively skewed distribution, the mean is less than the median, which is less than the mode. DIF: Cognitive Level: Analysis 9. In this illustration of a negatively skewed curve, identify which line represents the mode.

a. A b. B c. C ANS: C

In a skewed distribution, the mean, median, and mode are not equal. In a negatively skewed distribution, the mean is less than the median, which is less than the mode. The mode is the most frequently occurring value, and in a unimodal distribution, the mode is at the highest point of the curve.

DIF: Cognitive Level: Application 10. Which of the illustrations of distribution curves demonstrates the least amount of variation in

the scores?

a. b. c. d.

The least amount of variation would be in the first curve. The least amount of variation would be in the second curve. The least amount of variation would be in the third curve. The amount of variation can’t be defined by the curve.

ANS: A

Kurtosis explains the degree of peakedness of the curve, which is related to the spread or variance of scores. An extremely peaked curve is referred to as leptokurtic, an intermediate degree of kurtosis as mesokurtic, and a relatively flat curve as platykurtic. The less peaked the curve, the more variation is present. DIF: Cognitive Level: Application 11. What is the symbol for? a. Sample mean b. Population mean c. Population variance d. Sample variance ANS: A

Use of the terms statistic and parameter can be confusing because of the various populations referred to in statistical theory. A statistic, such as a mean ( ), is a numerical value obtained from a sample. A parameter is a true (but unknown) numerical characteristic of a population. For example, µ is the population mean or arithmetic average. The mean of the sampling distribution (mean of samples’ means) can also be shown to be equal to µ. A numerical value that is the mean ( ) of the sample is a statistic; a numerical value that is the mean of the population (µ) is a parameter. DIF: Cognitive Level: Comprehension 12. A researcher conducts a statistical test that reveals that the four groups analyzed differed. The

researcher wants to discover which one or ones of the four differed from the others. The researcher must then perform a post hoc analysis. What will this involve? a. Design of a second research study, using a new sample b. Descriptive statistics about the sample demographics c. Qualitative research generating new themes and ideas d. A second statistical test using the original data ANS: D

Post hoc analyses are commonly performed in studies with more than two groups when the analysis indicates that the groups are significantly different but does not indicate which groups are different. A post hoc analysis must be performed to determine which of the three groups are significantly different. In other studies, the insights obtained through the planned analyses generate further questions that can be examined with the available data. DIF: Cognitive Level: Application 13. Where would one find approximately 95% of the scores in the following example if scores are

normally distributed? “Scores ranged from 30 to 68, M = 45, SD = 7.” a. Between 37 and 61 b. Between 38 and 52 c. Between 31 and 59 d. Between 30 and 68 ANS: C

The range, standard deviation, and variance are statistics that describe the extent to which the values in the sample vary from one another. The most common of these statistics to be reported in the literature is the standard deviation because of its direct association with the normal curve. If the frequency distribution of any given variable is approximately normal, knowing the standard deviation of that variable allows us to know what percentages of subjects’ values on that variable fall between +1 and -1 standard deviation. When we calculate a standard deviation, we know that 34.13% of the subjects’ scores will be between the mean score and 1 standard deviation above the mean score. We also know that 34.13% of the subjects’ scores will be between the mean score and 1 standard deviation below the mean. The middle 95.44% of the subjects’ scores will be between -2 standard deviation and +2 standard deviations. DIF: Cognitive Level: Evaluation 14. If a researcher wishes to predict with 97.5% accuracy, the level of significance would be: a. 0.05. b. 0.01. c. 0.25. d. 0.025. ANS: D

If one wishes to predict with 97.5% accuracy, the level of significance (p) is 1 minus 97.5% (written as 0.975) = 0.025. In nursing research, alpha is usually set at 0.05, meaning that the researcher will allow a 5% or lower chance of making a Type I error. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. A researcher states in an article that a new experimental treatment, trialed in the outpatient

setting in a tri-physician practice in northern Oregon, produces better outcomes than the control treatment for patients with COPD. The p-value given is p < 0.05. What does this mean? (Select all that apply.) a. There is better than a 95% chance that at the research site mentioned in the article,

b. c. d. e.

the experimental treatment really does produce better outcomes for patients with COPD. The probability of error is 95%. There is very little chance that the intervention is effective—less than a 5% chance, in fact. There is better than a 95% chance that the experimental treatment will produce better outcomes for all COPD patients. There is less than a 5% chance that the researcher has reached this conclusion in error.

ANS: A, D, E

Probability theory addresses statistical analysis as the likelihood of accurately predicting an event or the extent of an effect. In probability theory, the researcher interprets the meaning of statistical results in light of his or her knowledge of the field of study. Probability is expressed as a lowercase p, with values expressed as percentages or as a decimal value ranging from 0 to 1. DIF: Cognitive Level: Synthesis 2. A null hypothesis is stated. The null hypothesis is, “There is no difference between 10 mcg

and 20 mcg of vitamin D3, in prevention of osteoporosis.” What are the implications of this statement, concerning the null hypothesis and Type I error? (Select all that apply.) a. Rejecting the null hypothesis when it actually is false means that the researcher has made a Type I error in concluding that there is a difference between 10 and 20 mcg of vitamin D3 in preventing osteoporosis. b. Making the statement is itself a Type I error. c. Whether the null hypothesis is true or not makes no difference, in terms of Type I error. d. Whether or not the researcher rejects the null hypothesis makes no difference, in terms of Type I error. e. Rejecting the null hypothesis when it actually is false means that the researcher concludes that there is a difference between 10 and 20 mcg of vitamin D3 in preventing osteoporosis, and there is no error. f. Rejecting the null hypothesis when it actually is true means that there is no difference between 10 and 20 mcg of vitamin D3 in preventing osteoporosis, but the researcher thinks there is, and has made a Type I error. ANS: E, F

The null hypothesis assumes no difference between groups, or no relationship between variables. Type I error is the probability of rejecting the null hypothesis when it is in fact true. Type I error is also called alpha []. In nursing research, alpha is usually set at 0.05, meaning that the researcher will allow a 5% or lower chance of making a Type I error. DIF: Cognitive Level: Analysis 3. A null hypothesis is stated. The null hypothesis is, “There is no difference between one baby

aspirin every day and no baby aspirin at all in prevention of myocardial infarction.” What are the implications of this statement, concerning the null hypothesis and Type II error? (Select all that apply.) a. Accepting the null hypothesis when it actually is true means that the researcher has

b. c. d. e.

made a Type II error in concluding that there is no difference between one baby aspirin every day and no baby aspirin in the prevention of myocardial infarction. Making the statement is itself a Type II error. Whether the null hypothesis is true or not makes no difference in terms of Type II error. Whether or not the researcher rejects the null hypothesis makes no difference, in terms of Type II error. Accepting the null hypothesis when it actually is true means that the researcher concludes that there is no difference between one baby aspirin and no baby aspirin every day in the prevention of myocardial infarction, and there is no error. Accepting the null hypothesis when it actually is false means that the researcher concludes that there is no difference between one baby aspirin and no baby aspirin every day in the prevention of myocardial infarction, when there actually is a difference. The researcher has therefore made a Type II error.

ANS: E, F

Type II error is the probability of retaining the null hypothesis when it is in fact false. Type II error is also called beta []. In nursing research, the beta is frequently set at 0.20, meaning that the researcher will allow for a 20% or lower chance of making a Type II error. DIF: Cognitive Level: Analysis 4. A researcher designs a study to measure the effect on patient satisfaction of the nurse stating

to the patient at least once a day, “You’re a good person.” The researcher sets the alpha (Type I error) for the study at p < 0.10 because the intervention costs nothing, it needs very little time to enact, and it is harmless. If the alpha is set at 0.10, what is the effect on the beta [], and on Type II error? (Select all that apply.) a. Beta [] stays the same. b. Type II error becomes less likely. c. Type II error becomes more likely. d. Beta [] decreases. e. Beta [] increases as well. f. Type II error stays the same. ANS: B, D

The researcher chooses the probability of making a Type I error when setting alpha [], and if the researcher decreases the probability of making a Type I error, the researcher increases the probability of making a Type II error []. By the same token, if the researcher sets the probability of making a Type I error quite high, perhaps 10%, the probability of making a Type II error decreases. DIF: Cognitive Level: Analysis 5. In statistical hypothesis testing, which of the following occur before the data are collected?

(Select all that apply.) a. The beta (Type II error) is set. b. A power analysis is conducted. c. The null hypothesis is accepted or rejected. d. The alpha (Type I error) is set. e. The primary null hypothesis is stated.

ANS: A, B, D, E

The following steps outline each of the components of statistical hypothesis testing: (1) state the null hypothesis; (2) set the study alpha (Type I error); (3) set the study beta (Type II error); (4) conduct a power analysis; (5) design and conduct the study; (6) compute the appropriate statistic on the obtained data; (7) compare the obtained statistic with its corresponding theoretical distributions in the reference tables. If the obtained statistic exceeds the critical value in the distribution table, the null hypothesis is rejected; if the obtained statistic is less than the critical value, the null hypothesis is accepted. DIF: Cognitive Level: Analysis 6. If beta, , is the probability of making a Type II error, what is 1 minus ? (Select all that

apply.) a. Alpha [] b. A relationship exists c. The power of the study d. The likelihood that the null hypothesis is incorrect e. The probability of not making a Type II error ANS: C, E

Power is the probability that a statistical test will detect an effect when it actually exists. Power is the inverse of Type II error and is calculated as 1 - . Type II error is the probability of retaining the null hypothesis when it is in fact false. When the researcher sets Type II error at 0.20 prior to conducting a study, this means that the power of the planned statistic has been set to 0.80. In other words, the statistic will have an 80% chance of detecting an effect if it actually exists. DIF: Cognitive Level: Analysis 7. A researcher is concerned about the power of a study. The researcher’s planned interventional

study examines the effect upon depression of instituting twice-yearly trips with the Road Scholar travel program for widows and widowers who have, 1 to 2 years before, lost a spouse to a long illness. What strategies could make Type II error less likely? (Select all that apply.) a. Decreasing the effect size b. Increasing the alpha from 0.05 to 0.10 c. Increasing the beta from 0.20 to 0.30 d. Decreasing the beta from 0.20 to 0.10 e. Decreasing the alpha from 0.05 to 0.025 f. Increasing the sample size ANS: B, D, F

The researcher chooses the probability of making a Type I error when setting alpha [], and if the researcher decreases the probability of making a Type I error, the researcher increases the probability of making a Type II error []. Power is the probability that a statistical test will detect an effect when it actually exists. Power is the inverse of Type II error and is calculated as 1 - . Type II error is the probability of retaining the null hypothesis when it is in fact false. When the researcher sets Type II error at 0.20 before conducting a study, this means that the power of the planned statistic has been set to 0.80. In other words, the statistic will have an 80% chance of detecting an effect if it actually exists. Reported studies failing to reject the null hypothesis (in which power is unlikely to have been examined) often have a low power level to detect an effect if one exists. Until more recently, the researcher’s primary interest was in preventing a Type I error. Therefore, great emphasis was placed on the selection of a level of significance but little emphasis was placed on power. This point of view is changing as we recognize the seriousness of a Type II error in nursing studies. Power analysis involves determining the required sample size needed to conduct the study. Cohen identified four parameters of power: (1) significance level, (2) sample size, (3) effect size, and (4) power (standard of 0.80). If three of the four are known, the fourth can be calculated by using power analysis formulas. Effect size is a constant; it is “the degree to which the phenomenon is present in the population or the degree to which the null hypothesis is false.” Consequently, if the researcher wants to increase a study’s power, the sample size must be increased, or the level of significance must be set at a less stringent level. DIF: Cognitive Level: Analysis 8. Findings can be statistically significant but clinically not significant. Which of the following

studies with statistically significant findings exemplify this? (Select all that apply.) a. Seventy-five seconds of UV light daily can completely reverse the symptoms of allergic dermatitis. b. Eating a cup of salad greens daily increases one’s life expectancy by 2 years. c. Petting a cat for 5 minutes daily increases one’s endorphin levels. d. Exercise Program Delta causes weight loss of 6.3 pounds per year in morbidly obese women. e. Talking to a crying baby calms the baby more than ignoring it; picking up the baby calms it more than talking to it. f. Medication R15B, taken daily from age 13, completely controls cystic acne by age 23. ANS: C, D, E, F

The findings of a study can be statistically significant but may not be clinically important. For example, one group of patients might have a body temperature 0.1° F higher than that of another group. Statistical analysis might indicate that the two groups are statistically significantly different. However, the findings have little or no clinical importance because of the small difference in temperatures between groups. Persons with dermatitis would find the UV light treatment almost miraculous. Two extra years of life may be clinically important to those with good quality of life. Increasing endorphins is not due only to petting cats, so this study is not particularly significant, clinically. A weight loss of 6.3 pounds per year is not large enough to make a significant difference in the life of morbidly obese women. Picking up crying babies is something that even one’s grandmother knows; this is not clinically useful. A medication that controls cystic acne 10 years later is of little use to the adolescent who is miserable with acne.

DIF: Cognitive Level: Analysis 9. A measured value is within two standard deviations of the mean but not within one standard

deviation, and it is greater than the mean. The distribution is very close to a normal distribution. What does this signify? (Select all that apply.) a. This particular value is not an outlier. b. In the data set, almost 2/3 of the values are closer to the mean than this one is. c. The data point falls within the majority of the measured values, in terms of its closeness to the mean. d. In the data set, at least 4% of the values are further from the mean than this particular value is. e. In this data set, between 65% and 95% of the values are smaller in value than this one is. ANS: A, B, D, E

The range, standard deviation, and variance are statistics that describe the extent to which the values in the sample vary from one another. The most common of these statistics to be reported in the literature is the standard deviation because of its direct association with the normal curve. If the frequency distribution of any given variable is approximately normal, knowing the standard deviation of that variable allows the reader to know what percentages of subjects’ values on that variable fall between +1 and -1 standard deviation. In a normal distribution, when a standard deviation is calculated, 34.13% of the values are between the mean score and 1 standard deviation above the mean. Similarly, 34.13% of the values are between the mean score and 1 standard deviation below the mean. The middle 95.44% of the subjects’ scores are between -2 standard deviations and +2 standard deviations. DIF: Cognitive Level: Synthesis 10. Which of the following are true about Type II error? (Select all that apply.) a. It is more likely to occur when p < 0.01 rather than when p < 0.05. b. It is extremely likely to occur when p < 0.001. c. It occurs when the null hypothesis is true but rejected. d. It is a possibility only when there are statistically nonsignificant results in a study. e. It is a possibility only when there are statistically significant results in a study. ANS: A, B, D

We choose the probability of making a Type I error when we set alpha, and if we decrease the probability of making a Type I error, we increase the probability of making a Type II error. The probability of retaining the null hypothesis when it is in fact false is a Type II error. In nursing research, beta is frequently set to 0.20, meaning that the researcher will allow for a 20% or lower chance of making a Type II error, when the alpha is set at 0.05. If the alpha decreases (becomes more stringent) (0.025, 0.01, and so forth), decreasing the possibility of Type I error, the consequence is that the beta rises, making Type II error much more likely. It is impossible to decrease both types of errors simultaneously without a corresponding increase in sample size. When a statistical test in a research study shows that a result is not statistically significant, the discerning reader will evaluate the sample size and the level of significance, in order to determine the possibility that a Type II error occurred. DIF: Cognitive Level: Analysis 11. Why might nonparametric statistical methods be used for analysis? (Select all that apply.)

a. b. c. d.

The level of measurement of the variables is nominal. The researcher prefers to use these statistical tests. The null hypothesis is absent. The sample is small or lacks a normal distribution.

ANS: A, D

The most commonly used type of statistical analysis is parametric statistics. The analysis is referred to as parametric statistical analysis because the findings are inferred to the parameters of a normally distributed population. These approaches to analysis require meeting the following three assumptions before they can justifiably be used: (1) normal distribution and variance can be calculated, (2) level of measurement at least interval, or ordinal with an approximately normal distribution, and (3) data that can be treated as a random sample. Nonparametric statistical analysis, or distribution-free techniques, can be used in studies that do not meet the first two assumptions of normal distribution and at least interval level data. DIF: Cognitive Level: Analysis 12. A teacher administers an examination. The examination seemed relatively easy for the

students, and the majority of the scores are at the high end of the scale, although several students received low scores. In statistical terms this represents what? (Select all that apply.) a. Positive skew b. Negative skew c. Asymmetrical distribution d. Symmetrical distribution e. A normal curve f. A non-normal curve ANS: B, C, F

whether the article’s statistics are correctly selected and applied? (Select all that apply.) a. Understand the discussion section of the article. b. Make a judgment as to whether the author’s interpretations of the data are correct. c. Make some judgment about whether the statistical procedures used were the correct ones for the level of measurement used for the study variables. d. Make some judgment about whether the statistical procedures used were the correct ones for the research question. e. Agree with the study’s stated limitations. f. Find the names of the statistical procedures the author used. ANS: A, B, C, D, F

To critically appraise the results section of a quantitative study, the reader needs to be able to (1) identify the statistical procedures used; (2) judge whether these statistical procedures were appropriate for the hypotheses, questions, or objectives of the study and for the data available for analysis; (3) comprehend the discussion of statistical analysis results; (4) judge whether the author’s interpretation of the results is appropriate; and (5) evaluate the clinical importance of the findings. DIF: Cognitive Level: Comprehension 14. A researcher is attempting to decide whether to hire a statistician to assist with the statistical

aspects of the study. If the researcher cannot perform all of the following for a quantitative study, why should a statistician be contacted? (Select all that apply.) a. Provide sample demographics using descriptive statistics. b. Perform reliability testing of the study instruments. c. Design and perform analyses to answer research questions and test hypotheses. d. Design and perform an exploratory analysis of the data. e. Hand-compute all statistical calculations. f. Prepare the data for analysis. g. Perform a power analysis. h. Interpret the results obtained by all statistical computations. ANS: A, B, C, D, F, G, H

To perform statistical analysis of data from a quantitative study, one must be able to (1) determine the necessary sample size to power the study adequately; (2) prepare the data for analysis; (3) describe the sample; (4) test the reliability of measurement methods used in the study; (5) perform exploratory analyses of the data; (6) perform analyses guided by the study objectives, questions, or hypotheses; and (7) interpret the results of statistical procedures. Early consultation with a statistician or expert researcher is recommended to help develop a plan for accomplishing these seven tasks. Descriptions of the sample demographics are made statistically. DIF: Cognitive Level: Application 15. A data set shows that the mean, median, and mode are the same. This means which of the

following? (Select all that apply.) a. The distribution is bimodal. b. The data are normally distributed. c. The variables are dichotomous. d. All data points are identical. e. The kurtosis is symmetrical. f. This may describe the normal curve. ANS: B, D, F

The theoretical normal curve is an expression of statistical theory. It is a theoretical frequency distribution of all possible scores. This theoretical normal curve is symmetrical and unimodal and has continuous values. The mean, median, and mode are equal. The distribution is completely defined by the mean and standard deviation. The data are normally distributed. If all data points are identical, their mean, median, and mode will be the same. DIF: Cognitive Level: Analysis

16. Why can Type I error and Type II error not be both present for one given hypothesis? (Select

all that apply.) a. Power analysis makes one type of error less likely. b. One refers to rejecting the null hypothesis when it is true and the other to accepting it when it is false. c. As beta rises, alpha falls. d. The researcher sets both the alpha level and the beta level. e. Qualitative research does not use power analysis. ANS: B, C

The researcher sets the values of two theoretical probabilities: (1) the probability of rejecting the null hypothesis when it is in fact true (alpha []; Type I error) and (2) the probability of retaining the null hypothesis when it is in fact false (beta []; Type II error). In nursing research, alpha is usually set at 0.05, meaning that the researcher will allow a 5% or lower chance of making a Type I error. The beta is frequently set to 0.20, meaning that the researcher will allow for a 20% or lower chance of making a Type II error. A Type II error occurs if the null hypothesis is regarded as true when, in fact, it is false. DIF: Cognitive Level: Comprehension 17. Which of the following are true in a skewed distribution? (Select all that apply.) a. Mean, mode, and median are not equal. b. The curve is asymmetrical. c. There is bimodal distribution. d. There is no mode. e. More than 50% of the values lie to one side of the mean. ANS: A, B, E

Any curve that is not symmetrical is referred to as skewed or asymmetrical. A curve may be positively skewed, which means that the largest portion of data is below the mean. A curve can also be negatively skewed, which means that the largest portion of data is above the mean. In a skewed distribution, the mean, median, and mode are not equal. In a positively skewed distribution, the mean is greater than the median, which is greater than the mode. In a negatively skewed distribution, the mean is less than the median, which is less than the mode. DIF: Cognitive Level: Analysis

Chapter 22: Using Statistics to Describe Variables Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. The figure below shows the frequency (f) distribution for a set of data. What is the set’s

mode? X 5 4 3 2 1 a. b. c. d.

f 1 0 2 3 1 4 3 2 1

ANS: C

The three measures of central tendency commonly reported in nursing studies include mode, median (MD), and mean ( ). The mode is the numerical value or score that occurs with the greatest frequency in a data set. It does not indicate the center of the data set. DIF: Cognitive Level: Analysis 2. In the data set below, what is the mean ( )?

X 5 4 3 2 1 a. b. c. d.

f 4 2 1 1 2 4 3.5 3 2.5

ANS: B

The three measures of central tendency commonly reported in nursing studies include mode, median (MD), and mean ( ). The mean is the arithmetic average of all the values of a variable in a study and is the most commonly reported measure of central tendency. The mean is the sum of the scores divided by the number of scores being summed. Mean ( ) = ÷ N = 35 ÷ 10 = 3.5. DIF: Cognitive Level: Analysis

3. The median is represented by which score for the following data set?

Data set: 1, 2, 4, 7, 7, 8, 10, 10, 10, 18 a. 10 b. 8 c. 7.5 d. 7 ANS: C

The median (MD) is the score at the exact center of the ungrouped frequency distribution. It is the 50th percentile. To obtain the MD, sort the values from lowest to highest. If the number of values is an uneven number, exactly 50% of the values are above the MD and 50% are below it. If the number of values is an even number, the MD is the average of the two middle values. The median for this set is 7.5, since the data set contains an even number of values, and the two numbers in the middle are 7 and 8. Their average is 7.5. DIF: Cognitive Level: Analysis 4. Which measure is the most helpful both for providing a quantification of dispersion and for

providing a way to interpret how far away from the mean each individual score is? a. Standard deviation b. Difference scores c. Range d. Magnitude ANS: A

Measures of dispersion, such as the range, difference scores, variance, and standard deviation, provide important insight into the nature of the data. The standard deviation is an important statistic, both for understanding dispersion within a distribution and for interpreting the relationship of a particular value to the distribution. DIF: Cognitive Level: Analysis 5. Which measure is merely a simple difference score? a. Standard deviation = 2.41 b. Difference scores = -2, -2, -1, +2, and +3 c. Range = 8 d. Variance = 5.80 ANS: C

The simplest measure of dispersion is the range. In published studies, range is presented in two ways: (1) the range is the lowest and highest scores, or (2) the range is calculated by subtracting the lowest score from the highest score. In this form, the range is a difference score that uses only the two extreme scores for the comparison. The range is generally reported in published studies but is not used in further analyses. DIF: Cognitive Level: Analysis 6. The data set is: 2, 3, 6, 7, 12. A measure of dispersion is calculated, and it is about 3.5. What

is this measure of dispersion? a. The difference score b. The variance

c. The range d. The standard deviation ANS: D

Standard deviation (s) is a measure of dispersion that is the square root of the variance. In published studies, sometimes the statistic reported by the researchers is SD. Either SD or s might be used in a research report to indicate the standard deviation for a study variable. The standard deviation is an important statistic, both for understanding dispersion within a distribution and for interpreting the relationship of a particular value to the distribution. DIF: Cognitive Level: Application 7. The data set is as follows: Ford, Ford, Chevy, Toyota, Ford, Ford, Chevy, Dodge, Dodge,

Dodge, Ford, Subaru, Chevy, Toyota, Chevy. What measure of central tendency and dispersion will be used with this set? a. Difference scores b. Range c. Median d. Mode ANS: D

The mode is the numerical value or score that occurs with the greatest frequency in a data set. The data in the sample data set are not inherently numerical in nature and represent only a nominal level of measurement. None of the listed measures of variability is suitable for nominal-level data. The mode is the only measure of central tendency appropriate for nominal data. DIF: Cognitive Level: Application 8. Twenty student nurses take the NCLEX examination. If the average of the 20 scores is known,

how many degrees of freedom are there in the sample? a. 18 b. 19 c. 20 d. 21 ANS: B

The concept of degrees of freedom was used in reference to computing a confidence interval. For any statistical computation, degrees of freedom is the number of independent pieces of information that are free to vary to estimate another piece of information. If, for instance, the mean and the total “n” are known, if all of the values except one are known, the last one can be calculated. However, if all except two are known, one has the freedom to vary, and the other one’s value is then set. In the case of the confidence interval, the degrees of freedom (df) are n - 1. This means that there are n - 1 independent observations in the sample that are free to vary (to be any value) to estimate the lower and upper limits of the confidence interval. DIF: Cognitive Level: Application MULTIPLE RESPONSE

1. The Stanford Binet Intelligence Quotient is a normed intelligence test, and its IQ measures are

quite normally distributed. Its standard deviation is 16. If the test were perfectly normal in its distribution, this would mean which of the following? (Select all that apply.) a. There are more people with IQs of 100 than any other number. b. For every person with an IQ of 120, there is one with an IQ of 80. c. More than 95% of people have IQs between 68 and 132. d. If someone’s IQ is measured as 109, and years later is measured as 112, someone else’s IQ has dropped three points. e. About 14% of people have IQs between 117 and 132. f. Excluding people with IQs of exactly 100, half of the remainder have IQs lower than 100, and the other half have IQs higher than 100. ANS: A, B, C, E, F

The normal curve is a perfectly symmetrical frequency distribution. The value at the exact center of a normal curve is the mean of the values. When a frequency distribution is shaped like the normal curve, we know that 34.13% of the subjects scored between the mean and 1 standard deviation above the mean and 34.13% of the subjects scored between the mean and 1 standard deviation below the mean. You can also say that 68.26% of the subjects scored between -1 and +1 standard deviations. This number is obtained by adding 34.13% and 34.13%. Because the normal curve is perfectly symmetrical, we also know that that 50% of the subjects scored above the mean, and 50% of the subjects scored below the mean. Furthermore, we can say that 95.44% of the subjects scored between -2 and +2 standard deviations. DIF: Cognitive Level: Synthesis 2. Female baccalaureate nursing students scored an average of 89% on the first midterm

examination. Male baccalaureate nursing students also scored an average of 89% on the first midterm examination. What does this mean? (Select all that apply.) a. The same number of men and women failed the test. b. If the passing score is 75%, fewer students failed in both groups than the number that passed. c. The overall combined average on the midterm, for both groups, is 89%. d. Both classes have the same range. e. Both classes have identical variances and standard deviations. f. The median score is the same for both classes. g. The mode score is the same for both classes. ANS: B, C

The mean is the arithmetic average of all the values of a variable in a study and is the most commonly reported measure of central tendency. The mean is the sum of the scores divided by the number of scores being summed. Consequently, it provides an average of the scores for each group. Combination of the groups provides the same group mean, since the means are identical. The values for mode and median are not provided, so no conclusions can be drawn about these. Measures of dispersion (standard deviation, range, variance) are not provided and cannot be assumed to be identical between groups. Since 100% (the highest possible passing score) and 74.9% (the highest possible failing score) average 87.5% and the overall combined mean is higher than this, more students passed than failed in both groups, and this is true, as well, for the combined group.

DIF: Cognitive Level: Synthesis 3. There is a data set A: 3, 3, 3, 5, 6, 6, 8, 9, 9, 12, 13.

The data set B is created. It is identical to A, except for its much larger last value. Data set B: 3, 3, 3, 5, 6, 6, 8, 9, 9, 12, 83. What is the effect of increasing the largest value upon the descriptive statistics of the data set? (Select all that apply.) a. The mean increases. b. The median increases. c. The mode increases. d. The set’s distribution changes from perfectly normal to somewhat skewed. e. The standard deviation increases. f. The variance increases. g. The range increases. ANS: A, D, E, F, G

The mode is the numerical value or score that occurs with the greatest frequency in a data set. It does not indicate the center of the data set; therefore, unless this is the largest value, the mode will be unaffected. The median (MD) is the score at the exact center of the ungrouped frequency distribution. It is the 50th percentile and would be unaffected by a change in the value of the largest value. The mean is the arithmetic average of all the values of a variable in a study and is the most commonly reported measure of central tendency. The mean is the sum of the scores divided by the number of scores being summed. The mean is sensitive to extreme scores such as outliers. An outlier is a value in a sample data set that is unusually low or unusually high in the context of the rest of the sample. Therefore, the mean will be affected by a large increase in the largest value. Measures of dispersion or variability are measures of individual differences of the members of the population and sample. Since they indicate how different the scores are, they all are affected by an extreme value. DIF: Cognitive Level: Evaluation 4. Descriptive statistics are found in which of the following? (Select all that apply.) a. All quantitative descriptive research reports b. Some qualitative research reports c. All quantitative inferential research reports d. No qualitative research reports e. Some quantitative inferential research reports ANS: A, B, C

For some types of studies, descriptive statistics are the only approach to analysis of the data. For other studies, descriptive statistics are the first step in the statistical analysis process, to be followed by inferential statistics. For all studies that involve numerical data, descriptive statistics are crucial in understanding the fundamental properties of the variables being studied. DIF: Cognitive Level: Application 5. A researcher wants to select a way to measure how values in a research study are dispersed

around the mean, and how homogeneous or heterogeneous they are, for a ratio-level variable. The researcher might select which of the following? (Select all that apply.) a. Mode b. Range

c. Frequency distribution d. Mean e. Standard deviation ANS: B, E

Measures of dispersion or variability are measures of individual differences of the members of the population and sample. They indicate how values in a sample are dispersed around the mean. These measures provide information about the data that is not available from measures of central tendency. They indicate how different the scores are—the extent to which individual values deviate from one another. If the individual values are similar, measures of variability are small, and the sample is relatively homogeneous in terms of those values. When there are wide variations or differences in the scores, the sample is considered heterogeneous. The heterogeneity of sample scores or values is determined by measures of dispersion or variability. The measures of dispersion most commonly reported in nursing research are range, difference scores, variance, and standard deviation. All are useful for ratio-level data. DIF: Cognitive Level: Application 6. The confidence interval for 5-year survival after Stage I breast cancer, in a large sample of

women living in Texas, is 87.5% to 93.3%, at a p < 0.05 level of significance. What does this mean? (Select all that apply.) a. Texan women in the near future will be likely to have about a 90% chance of living 5 years after they are newly diagnosed with Stage I breast cancer. b. Women in Texas with Stage I breast cancer have a 95% chance of 90% survival, over a 5-year period. c. Women in Texas with Stage I breast cancer have an 86% chance of 5-year survival. d. In any sample of women in Texas newly diagnosed with Stage I breast cancer, there is about a 95% chance that their collective survival 5 years from now will be around 90%. e. Women in Texas can feel 95% confident that they will survive Stage I breast cancer. ANS: A, D

To determine how closely the sample mean approximates the population mean, or the sample proportion approximates the population proportion, the standard error is used to build a confidence interval. A confidence interval can be created for many statistics, such as a mean, proportion, odds ratio, and correlation. At the p < 0.05 level, the confidence interval in the example merely signifies that there is a window of possibilities, and future samples have a 95% chance of falling within that window. DIF: Cognitive Level: Application

Chapter 23: Using Statistics to Examine Relationships Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. Which correlation coefficient shows the strongest relationship? a. 0.10 b. -0.85 c. 0.80 d. -0.42 ANS: B

The Pearson product-moment correlation was one of the first of the correlation measures developed and is the most commonly used. This coefficient (statistic) is represented by the letter r, and the value of r is always between -1.00 and +1.00. A value of zero indicates no relationship between the two variables. A positive correlation indicates that higher values of X are associated with higher values of Y, and lower values of X are associated with lower values of Y. A negative or inverse correlation indicates that higher values of X are associated with lower values of Y. An r value equal to 0.50 is a moderate positive relationship, and an r value equal to -0.50 is a moderate negative or inverse relationship. Consequently, a relationship of -0.85 is the strongest relationship, and it is a negative or inverse correlation. DIF: Cognitive Level: Analysis 2. The Pearson product-moment correlation for two variables, fear of embarrassment and anxiety

just before making an oral presentation, is r = 0.78, with a coefficient of determination of 0.6084. This means that what percentage of anxiety just before making an oral presentation can be attributed to fear of embarrassment? a. About 0.61% b. About 61% c. About 0.78% d. About 78% ANS: B

One can also assess the magnitude of association by obtaining the coefficient of determination for the Pearson correlation. Computing the coefficient of determination simply involves squaring the r value. The r2 (multiplied by 100%) represents the percentage of variance shared between the two variables. In other words, the coefficient of determination explains how much of the change in value of one variable can be attributed to the fluctuation in value of the other variable. DIF: Cognitive Level: Analysis 3. What does the correlational diagram X Y mean? a. X obviously precedes Y in time. b. X is interchangeable with Y. c. There is a relationship between X and Y. d. Either X causes Y, or Y causes X. ANS: C

Correlational analyses identify relationships or associations among variables. In the diagram, the arrow points to both variables, further confirming that one doesn’t cause the other: X is merely related to Y and nothing more. DIF: Cognitive Level: Comprehension 4. A researcher develops a new instrument for measuring adjustment to widowhood in

dependents whose spouses were killed in armed conflict. The researcher’s initial instrument contains 55 items, and the researcher wants to trim these down to 25 or 30 but doesn’t want to lose any of the main concepts. What method of statistical analysis will the researcher use, in order to pare this tool down to a manageable size without loss of content? a. Kendall’s tau b. Spearman’s rho c. Linear regression analysis d. Factor analysis ANS: D

Factor analysis refers to a collection of statistical techniques designed to examine interrelationships among large numbers of variables to reduce them to a smaller set of variables and to identify clusters of variables that are most closely linked together (factors). DIF: Cognitive Level: Application 5. A study examines the relationship between strength of belief in previous lives (Yes, Not Sure,

and No) and percentage of butterfat in milk most commonly purchased (Non-Fat, 1%, 2%, Whole). The data could be analyzed by which statistical test? a. Kendall’s tau b. Pearson product-moment correlation c. Principal components analysis d. Bland and Altman plot ANS: A

If one or both of two study variables do not meet the assumptions for a Pearson correlation, or if the variables are scaled on an ordinal scale of measurement (rather than interval or ratio), both the Spearman’s rank-order correlation coefficient and Kendall’s tau are more appropriate statistics. The Spearman’s rank-order correlation coefficient and Kendall’s tau calculations involve converting the data to ranks, discarding any variance or normality issues associated with the original values. DIF: Cognitive Level: Analysis 6. A Pearson correlational analysis examines the relationship between variable A, hours of sleep

per week, and B, symptom severity, in 43 women with post-polio syndrome. In accessing the table of values, the researcher should use which number for degrees of freedom? a. 2 b. 4 c. 41 d. 43 ANS: C

Every inferential statistic has its own formula for degrees of freedom (numbers of values that are free to vary). The formula for degrees of freedom (df) for a Pearson r is n - 2. Thus, in this case, the df is 43 - 2 = 41. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. In the results and conclusions sections of a research paper about predelinquent behavior, the

researcher mentions the strong correlational relationship between the number of incidents of predelinquent behavior and the number of hours the mother works outside the home. What does the author imply by stating this? (Select all that apply.) a. Some sort of test of correlation was performed, and it reached statistical significance. b. As number of hours worked outside the home varied, so did the frequency of incidents of predelinquent behavior. c. Having a mother work many hours outside the home causes predelinquent behavior. d. Incidents of predelinquent behavior cause mothers to work more and more hours outside the home. e. As number of hours worked outside the home increased, so did the frequency of incidents of predelinquent behavior. f. The researchers avoided a Type II error, in relation to the association between these two variables. g. The researchers operationalized the two study variables. ANS: A, B, F, G

history of being underweight during the first 2 years of life, the researcher mentions the strong negative correlation between these two variables. What does the author imply by stating this? (Select all that apply.) a. Some sort of test of correlation was performed, and it reached statistical significance. b. A person with morbid obesity is more likely than someone without it to have been underweight during the first 2 years of life. c. A person with morbid obesity is less likely than someone without it to have been underweight during the first 2 years of life. d. Having been underweight during the first 2 years of life prevents morbid obesity in

adulthood. e. The statement above contains the researchers’ operationalizations of the two study variables. ANS: A, C

Bivariate correlational analysis measures the magnitude of a linear relationship between two variables and is performed on data collected from a single sample. Correlational analysis provides two pieces of information about the data: the nature or direction of the linear relationship (positive or negative) between the two variables and the magnitude (or strength) of the linear relationship. DIF: Cognitive Level: Comprehension 4. What is the connection between a scatter plot and a calculation of correlation? (Select all that

apply.) a. Constructing a scatter plot allows the researcher to visualize in advance whether a calculation of linear correlation is likely to reveal a relationship between the variables. b. Constructing a scatter plot produces a correlation coefficient, as does calculating a correlation. c. A calculation of correlation should be performed before constructing a scatter plot, because the calculation is more scientific. d. The scatter plot provides a visual representation of the connection between two variables; a correlational calculation provides a quantification of the connection between the same variables. e. Just like calculation of correlation, constructing a scatter plot provides a way to quantify explained variance. ANS: A, D

Scatter plots or scatter diagrams provide useful preliminary information about the nature of the relationship between variables. The researcher should develop and examine scatter diagrams before performing correlational analysis. Scatter plots may be useful for selecting appropriate correlational procedures, but most correlational procedures are useful for examining linear relationships only. A scatter plot can easily identify nonlinear relationships; if the data are nonlinear, the researcher should select statistical alternatives such as nonlinear regression analysis. A scatter plot is created by plotting the values of two variables on an x-axis and a y-axis. DIF: Cognitive Level: Analysis 5. For which of the following levels of measurement would a parametric statistical test like the

Pearson product-moment correlation coefficient be used? (Select all that apply.) a. Nominal level b. Ordinal level c. Interval level d. Ratio level e. Dichotomous ANS: C, D

The Pearson product-moment correlation coefficient is used to determine the relationship between two variables measured at least at the interval level of measurement. Nominal level of measurement is the lowest of the four measurement levels or categories. It is used when data can be organized into categories of a defined property but the categories cannot be ordered. In interval level of measurement, distances between intervals of the scale are numerically equal. However, it is not possible to provide the absolute amount of the attribute because of the absence of a meaningful zero point on the interval scale. Ratio level of measurement is the highest form of measure and meets all the rules of the lower forms of measures: mutually exclusive categories, exhaustive categories, rank ordering, equal spacing between intervals, and a continuum of values. In addition, ratio level measures have absolute zero points. DIF: Cognitive Level: Analysis 6. Which of the following variables are able to be analyzed using the Pearson product-moment

correlation? (Select all that apply.) a. Age b. Race c. Gender d. Score on the Spielberger State Trait Anxiety Inventory (STAI) e. Years of education f. Temperature g. Nickname h. Whether or not patient has advanced directives ANS: A, D, E, F

The Pearson product-moment correlation coefficient is used to determine the relationship between two variables measured at least at the interval level of measurement. In this example, they would be only the four: age, score on the STAI, years of education, and temperature. Nominal level of measurement is the lowest of the four measurement levels or categories. It is used when data can be organized into categories of a defined property but the categories cannot be ordered. In interval level of measurement, distances between intervals of the scale are numerically equal. However, it is not possible to provide the absolute amount of the attribute because of the absence of a zero point on the interval scale. Ratio level of measurement is the highest form of measure and meets all the rules of the lower forms of measures: mutually exclusive categories, exhaustive categories, rank ordering, equal spacing between intervals, and a continuum of values. In addition, ratio level measures have absolute zero points. DIF: Cognitive Level: Application 7. Twelve research studies show a strong correlation between low levels of education and

poverty. A social scientist declares that the “cure” for poverty is in free education for all of the children of the poor. What are valid arguments against this declaration? (Select all that apply.) a. The scientist believes that a low level of education, in and of itself, causes poverty, but no study has demonstrated this. b. It is possible that low levels of education cause Item B, and Item B causes poverty. c. It is possible that multigenerational poverty causes lower levels of education. d. It is possible that low levels of education and poverty are both caused by social injustice. e. Twelve correlational research studies are not enough to demonstrate cause: at least 50 studies of 100 subjects each would be required for this. ANS: A, B, C, D

Correlational analysis provides two pieces of information about the data: the nature or direction of the linear relationship (positive or negative) between the two variables and the magnitude (or strength) of the linear relationship. Correlation statistics are not an indication of causality, no matter how strong the statistical result. DIF: Cognitive Level: Application 8. The calculated Pearson r was -0.95 in a research study on number of hours parents spent at

children’s sporting events and number of arrests those children had experienced by age 30. What does this Pearson r value signify? (Select all that apply.) a. No relationship b. Weak linear relationship c. Moderate linear relationship d. Strong linear relationship e. Positive relationship f. Inverse relationship g. Negative relationship ANS: D, F, G

Correlational analysis provides two pieces of information about the data: the nature or direction of the linear relationship (positive or negative) between the two variables and the magnitude (or strength) of the linear relationship. In a positive linear relationship, the values being correlated vary together (in the same direction). When one value is high, the other value tends to be high; when one value is low, the other value tends to be low. In a negative linear relationship, when one value is high, the other value tends to be low. The Pearson product-moment correlation was one of the first correlation measures developed and is the most commonly used. This coefficient is represented by the letter r, and the value of r is always between -1.00 and +1.00. A value of zero indicates no relationship between the two variables. The further the value from zero, the stronger the relationship. A positive correlation indicates that higher values of X are associated with higher values of Y, and lower values of X are associated with lower values of Y. A negative or inverse correlation indicates that higher values of X are associated with lower values of Y. An r value equal to 0.50 is a moderate positive relationship and an r value equal to -0.50 is a moderate negative or inverse relationship. A correlational value near -1 signifies a strong negative relationship, and a value near +1 signifies a strong positive relationship. DIF: Cognitive Level: Analysis

Chapter 24: Using Statistics to Predict Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A researcher is studying daily carbohydrate intake and the next day’s first morning blood

glucose monitor value. After drawing a scatter plot, the researcher develops a multiple regression equation. What is does the value R represent? a. The line of best fit b. The amount of change in blood glucose monitor values that daily carbohydrate intake predicts c. Daily carbohydrate intake times blood glucose monitor value d. The correlation between daily carbohydrate intake and the next day’s first morning blood glucose monitor value ANS: D

The multiple R is defined as the correlation between the actual y values and the predicted y values using the new regression equation. The R2 represents the percentage of variance explained by y by the predictor, and is called the coefficient of determination. DIF: Cognitive Level: Application 2. A researcher is studying stress and various factors that seem to be related to it, in women with

terminally ill spouses. Among other things, the researcher finds out that depression contributes to total stress; depression contributes to lack of exercise; exercise contributes to depression; exercise relieves stress; guilt contributes to depression; exercise has no effect on guilt, but it affects total stress; stress worsens depression; and stress decreases motivation to perform exercise. This is an example of what problem commonly encountered in regression analyses? a. Multicollinearity b. Hazard ratio c. Odds ratio d. Predictive validity ANS: A

Multicollinearity occurs when the independent variables in a multiple regression equation are strongly correlated with one another. The presence of multicollinearity does not affect predictive power (the capacity of the independent variables to predict values of the dependent variable in a specific sample); rather it causes problems related to generalizability and the stability of the findings. The first step in identifying multicollinearity is to examine the correlations among the independent variables. DIF: Cognitive Level: Application 3. Why does a researcher decide to calculate odds ratio instead of calculating linear regression,

when comparing whether a person voted in the last election, and the person’s gender? a. Voting records are sealed. b. Both predictor and dependent variable are dichotomous. c. Odds ratio is a simpler calculation. d. Strength of relationship is not an issue.

ANS: B

When both the predictor and the dependent variable are dichotomous (having only two values), the odds ratio is a commonly used statistic to obtain an indication of association. The odds ratio (OR) is defined as the ratio of the odds of an event occurring in one group to the odds of it occurring in another group. Put simply, the OR is a way of comparing whether the odds of a certain event is the same for two groups. Linear regression is a procedure that estimates the value of a dependent variable based on the value of an independent variable. In simple linear regression, the dependent variable is continuous, and the predictor can be any scale of measurement. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. A researcher collects a nationally based set of data about cholesterol levels and age at first

circulatory incident (myocardial infarction or cerebrovascular accident). The researcher performs a linear regression analysis, in order to do which of the following? (Select all that apply.) a. To be able to estimate the age at which circulatory incidents are likely to occur, given the cholesterol level. b. To determine how well the data fit the theoretical framework c. To calculate the strength of the relationship between cholesterol levels and circulatory incidents d. To determine whether there is a linear relationship between cholesterol levels and circulatory incidents e. To derive the formula for the line of best fit f. To obtain information from which to construct a better scatter plot ANS: A, C, D, E

Simple linear regression is a procedure that estimates the value of a dependent variable based on the value of an independent variable. Simple linear regression is an effort to explain the dynamics within the scatter plot by developing a straight line (the line of best of fit) through the plotted scores. This line is drawn to best explain the linear relationship or association between two variables. Knowing that linear relationship, we can, with some degree of accuracy, use regression analysis to predict the value of one variable if we know the value of the other variable. This has nothing to do with a theoretical framework. DIF: Cognitive Level: Application 2. A researcher draws a scatter plot of study data. The researcher develops a multiple regression

equation and determines R2 as 0.5625. What does the calculated value R2 represent? (Select all that apply.) a. It means the standard error, squared. b. It means that the predictor variables accounted for 56.3% of the variance in the outcome variable. c. It stands for the standard deviation of the data set y, squared. d. It estimates shrinking regression. e. It is the coefficient of determination. f. It is the explained variance.

ANS: B, E, F

The multiple R is defined as the correlation between the actual y values and the predicted y values using the new regression equation. The R2 represents the percentage of variance explained in y by the predictor and is called the coefficient of determination. R2 was 0.285, indicating that patient trust and depression accounted for 28.5% of the outcome variable. DIF: Cognitive Level: Analysis 3. Which of the following terms in correlational research mean the same thing? (Select all that

apply.) a. Predictor variable b. Dichotomous variable c. Dependent variable d. Multicollinearity e. Independent variable ANS: A, E

In regression analysis, the independent (predictor) variable or variables influence variation or change in the value of the dependent variable. The goal is to determine how accurately one can predict the value of an outcome (or dependent) variable based on the value or values of one or more predictor (or independent) variables. Multicollinearity occurs when the independent variables in a multiple regression equation are strongly correlated with one another; this may result in unstable and less generalizable findings. A dichotomous variable has only two possible values. DIF: Cognitive Level: Comprehension 4. A researcher conducts research on optimism. The researcher is calculating a multiple

regression equation to predict levels of optimism and wishes to consider religious affiliation as one of the predictor variables. The researcher creates several dummy variables, for this purpose. Why must this be done? (Select all that apply.) a. It is safer to create more variables than less, since they may each contribute. b. Multiple regression requires that the researcher enter numerical values, not names such as Lutheran, Orthodox Jewish, Buddhist, Islamic, and so forth. c. Reducing nominal or categorical data to one or a series of dichotomous values allows mathematical computation of the regression equation. d. Religious affiliation is a protected entity under HIPAA and must be coded before it is used in calculations. e. The researcher’s aim is to develop a formula with which to calculate optimism, given certain other variables, so these must all be represented as numbers. ANS: B, C, E

Variables in a regression equation can take many forms. Traditionally, as with most multivariate analyses, variables are measured at the interval or ratio level. However, researchers also use categorical or dichotomous variables (referred to as dummy variables), multiplicative terms and transformed terms. A mixture of types of variables may be used in a single regression equation. To use categorical variables in regression analysis, a coding system is developed to represent group membership. If a variable is dichotomous, such as gender, members of one category are assigned the number 1 (e.g., female) and all others are assigned the number 0 (e.g., male). If the categorical variable has three values, two dummy variables are used to represent them. When more than three categories define the values of the variable, increased numbers of dummy variables are used. DIF: Cognitive Level: Analysis 5. What is a multiple regression equation? (Select all that apply.) a. One that represents the mathematical effect that several independent variables have

on the dependent variable b. One in which the x-values are multiplied by one another c. One that explains more of the variance in y than does a single linear regression

equation d. An experimental model for determining best practices e. One that uses more than one predictor variable to predict the value of the outcome f.

variable One that explains all of the variance in the dependent variable, in terms of several independent variables

ANS: A, C, E

Multiple linear regression analysis is an extension of simple linear regression in which more than one independent variable is entered into the analysis. Because the relationships between multiple predictors and y are tested simultaneously, the calculations involved in multiple regression analysis are very complex. Multiple regression is best conducted using a statistical software package. A multiple regression formula explains some or much of the variance in the dependent variable; it cannot explain all of it. DIF: Cognitive Level: Analysis 6. Why does a researcher decide to use logistic regression instead of linear regression to

calculate survival odds after suffering an out-of-hospital heart attack, in persons of various ages, genders, and cardiac diagnoses? (Select all that apply.) a. Survival versus nonsurvival is a dichotomous variable. b. Having a heart attack is a variable that has many possible outcomes. c. Linear regression is less logical than is logistic regression. d. Age is a ratio-level variable. e. Gender is a nominal-level variable. f. Cardiac diagnosis is a nominal-level variable. ANS: A, D, E, F

Logistic regression replaces linear regression when the researcher wants to test a predictor or predictors of a dichotomous dependent variable. The output yields an adjusted OR for each predictor, meaning that each predictor’s OR represents the relationship between that predictor and Y, after adjusting for the presence of other predictors in the model. As is the case with multiple linear regression, each predictor serves as a covariate to every other predictor in the model. Logistic regression can have continuous predictors, nominal predictors, or a combination of the two, with no assumptions regarding normality of the distribution. DIF: Cognitive Level: Analysis 7. Which of the following dependent variables is suitable for logistic regression analysis? (Select

all that apply.) a. How many compressions were delivered in the first minute following the call of a code blue b. Serum sodium value c. Born on earth—not born on earth d. Height at adulthood e. Birth gender f. Whether a patient with cancer goes into remission ANS: C, E, F

Logistic regression replaces linear regression when the researcher wants to test a predictor or predictors of a dichotomous dependent variable. Logistic regression can have continuous predictors, nominal predictors, or a combination of the two, with no assumptions regarding normality of the distribution. DIF: Cognitive Level: Analysis 8. A researcher decides to study how many college freshmen with continuous enrollment

graduate within 4, 4.5, 5, 5.5, and 6 years and to analyze this according to what their majors at graduation are, as well as other demographic variables. Why would a Cox proportional hazards regression analysis be suitable for this research? (Select all that apply.) a. Demographic variables could affect time until graduation. b. The data of people who do not graduate at all may be informative. c. Attendance at college can present hazard. d. A predictor of the dependent variable is time-related. e. Only people who actually graduate by the end of 12 semesters will have their data analyzed. ANS: A, B, D

The purpose of a regression analysis is to predict or explain as much of the variance in the value of a dependent variable as possible. The major difference between using Cox regression as opposed to linear regression is the ability of survival analysis to handle cases where survival time is unknown. Logistic regression yields odds ratios for each predictor to represent the relationship between that predictor and y, whereas Cox regression yields hazard ratios. DIF: Cognitive Level: Application 9. Which of the following statements about prediction is true? (Select all that apply.) a. Simple linear regression can predict possible changes in A, given B. b. Multicollinearity is used to provide definitive attribution in predicting dependent

c. d. e. f.

variables with similar outcomes. Multiple regression can provide information about the strongest predictors, C, D, E, and F, associated with an outcome variable G. Odds ratio is used to predict the likelihood of a dichotomous event, in the light of a different dichotomous variable Logistic regression is used to predict a dichotomous variable, using a variety of other variables. Cox hazard regression can predict the likelihood of an event occurring at certain points in time.

ANS: A, C, D, E, F

Simple linear regression provides a means to estimate the value of a dependent variable based on the value of an independent variable. Multicollinearity occurs when the independent variables in a multiple regression equation are strongly correlated with one another. Multiple regression analysis is an extension of simple linear regression in which more than one independent variable is entered into the analysis to predict a dependent variable. When both the predictor and the dependent variable are dichotomous (having only two values), the odds ratio is a commonly used statistic to obtain an indication of association. Logistic regression replaces linear regression when the researcher wants to test a predictor or predictors of a dichotomous dependent variable. Logistic regression can have continuous predictors, nominal predictors, or a combination of the two, with no assumptions regarding normality of the distribution. The major difference between using Cox regression as opposed to linear regression is the ability of survival analysis to handle cases where survival time is unknown. Logistic regression yields odds ratios for each predictor to represent the relationship between that predictor and y, whereas Cox regression yields hazard ratios. DIF: Cognitive Level: Comprehension

Chapter 25: Using Statistics to Determine Differences Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. What does the two-way chi-square test measure? a. Whether one variable seems related to another one b. Whether two variables cause one another c. Whether an intervention changes the dependent variable’s value d. Change over time ANS: A

The chi-square (c2) test compares differences in proportions of nominal level variables. A two-way chi-square is a statistic that tests whether proportions in levels of one variable are significantly different from proportions of the second variable. In other words, it detects whether one nominal variable seems to be related to another one. DIF: Cognitive Level: Analysis 2. In an ANOVA calculation evaluating causation, the mean square within groups value

represents the ordinary amount of variation that exists in the data set. What does the mean square between groups value represent? a. The effect produced by the interventional conditions b. The average of all variations in the data set c. Total variation d. The differences that exist among the several interventional conditions ANS: A

The term “mean square” (MS) is used interchangeably with the word “variance.” The formulas for ANOVA compute two estimates of variance: the between groups variance and the within groups variance. The between groups variance represents differences between the groups/conditions being compared, and the within groups variance represents differences among (within) each groups’ data. DIF: Cognitive Level: Analysis 3. Which test is essentially a comparison of means? a. Mann-Whitney U b. Chi-square c. Wilcoxon signed-rank test d. t-test ANS: D

One of the most common parametric analyses used to test for significant differences between group means of two samples is the t-test. In its calculation, the mean difference of scores is the numerator. In addition, the test uses the pooled standard deviation of the two samples as the denominator. Mann-Whitney U calculations involve converting the data to ranks, discarding any variance or normality issues associated with the original values. The Wilcoxon signed-rank test calculations involve converting the data to ranks, discarding any variance or normality issues associated with the original values. The chi-square (c2) test compares differences in proportions of nominal level variables. DIF: Cognitive Level: Comprehension 4. Why is post hoc statistical testing not performed with a two-group ANOVA? a. A researcher is reluctant to perform a post hoc analysis that would require a more

stringent level of significance. b. The F-statistic would be invalidated by the second test. c. If hypothesis testing reveals that a difference between groups exists, it is obvious what two groups those are. d. Sample sizes are not large enough for this analysis. ANS: C

Post hoc tests have been developed specifically to determine the location of group differences after ANOVA is performed on data from more than two groups. These tests were developed to reduce the incidence of a Type I error. Frequently used post hoc tests are the Tukey Honestly Significant Difference (HSD) test, the Newman-Keuls test, the Scheffé test, and the Dunnett test. The post hoc analyses performed after the ANOVA preserve the same level of analysis as the ANOVA itself. The F-statistic is not invalidated by performing a post hoc analysis. Sample size is not a consideration when performing a post hoc analysis. DIF: Cognitive Level: Analysis 5. What is unique about chi-square analysis? a. It is almost always statistically significant. b. It is used for two nominal variables. c. It demands normal distribution, even of dichotomous variables. d. It is parametric. ANS: B

The chi-square (c2) test compares differences in proportions of nominal level variables. Statistical significance may or may not exist. The test does not demand normal distribution, and it is nonparametric. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. Below the third table in a research report, concerning switching infants to cow’s milk at 6

months of age instead of 12 months, is a notation: “t(22) = -0.76, p = .41” What does this mean? (Select all that apply.) a. A t-test was performed. b. Apparently 24 subjects participated in the study.

c. There was a difference between groups. d. The difference between groups was not statistically significant. e. If there was an intervention, the intervention was more effective than the control

condition. f. The results are generalizable. g. The researcher failed to reject the null hypothesis. h. A Type I error occurred. ANS: A, B, C, D, G

The notation that represents the research results contains several elements. First is the letter that represents the statistical test, in this case t, followed, in parentheses, by the degrees of freedom. For this test of the difference between two means, the degrees of freedom would be the number of subjects in the study, minus the number of groups (2). After the equals sign is the t-statistic value of -0.76, representing the solution of the equation. Last is p = 0.41, far greater than 0.05, meaning that the probability of the amount of difference between group means was within normal expectations, signifying that the null hypothesis was not rejected. There was no significant difference between the means of the two groups: in other words, the switch to cow’s milk at 6 months was not that different from what the values would be at 12 months. In this particular case, not enough is known about the research to discern in which group the intervention was more “effective.” Type I error is rejecting the null hypothesis in error: since the null hypothesis was not rejected, Type I error did not occur. DIF: Cognitive Level: Synthesis 2. A researcher is conducting a study to discover whether the provision of hypnosis with dental

work affects pain. The researcher’s three groups are (1) hypnosis before and during the procedure, (2) hypnosis before but not during the procedure, and (3) no hypnosis. If the researcher plans to use an ANOVA for the statistical analysis, which would be an acceptable way to measure pain, for this study? (Select all that apply.) a. Present versus absent b. Worse ... Some ... A Lot ... Unbearable c. 0- to 100-point verbal numerical scale d. Systolic blood pressure readings e. The force with which the subject squeezes a rubber ball with pressure gauge attached ANS: C, D, E

The ANOVA can be used if the assumptions for parametric analysis are achieved and if study data are at least at the interval level. Nominal level of measurement is the lowest of the four measurement levels or categories. It is used when data can be organized into categories of a defined property, and the categories are mutually exclusive and exhaustive, but the categories cannot be ordered. Nomina in Latin means name. Data that can be measured at the ordinal level can be assigned to categories of an attribute that can be rank-ordered. With ordinal level data, the quantity of the attribute possessed can be identified. However, it cannot be shown that the intervals between the ranked categories are equal. At the interval level of measurement, distances between intervals of the scale are numerically equal. Interval scales are assumed to be a continuum of values. The ratio level is the highest form of measurement. In addition, ratio level measures have absolute zero points: the value of zero indicates that there is an absence of the property being measured.

DIF: Cognitive Level: Analysis 3. A statistician measures the difference in songbird warble variation in 25 mockingbirds, both

before and after nutritional supplementation with Dr. Petit Oiseau’s Musical Bird Seed. Warble variation is determined by a computer program that detects sound frequency and pattern changes during a 15-minute period twice a day, and these data are averaged to represent number of warble variations per minute. What considerations determine choice of a test for this research? (Select all that apply.) a. The sample size is small to moderate. b. There is one group of birds and all receive the treatment. c. A before-after type of design is used. d. The independent variable is at the nominal level. e. Birds are divided into two groups. f. The independent variable is ratio level. g. The dependent variable is ratio level. ANS: A, B, C, D, G

The independent variable, without the special bird seed versus with the special bird seed, has only two values, so it exists at the nominal level. The dependent variable is warble variations per minute, which uses the real number scale on which zero means zero, so it is a ratio-level variable, making parametric analysis possible. Twenty-five is a small to moderate size sample, adequate for parametric comparisons. For ratio-level and interval-level dependent variables, parametric statistics are appropriate. Parametric statistical tests covered in this chapter that are used to determine differences are the independent samples t-test, paired or dependent samples t-test, and analysis of variance (ANOVA). So sample size, number of groups, design type, and measurement levels of the independent and dependent variables determine the appropriate statistical test. There is one group of birds, in a before-after design, so the ANOVA is not appropriate. The two measurements are not independent of one another, since the baseline measurement values will affect the second measurement’s values. This leaves only the paired or dependent samples t-test as the appropriate choice. How one interprets the results of these statistics depends on the design of the study. DIF: Cognitive Level: Analysis 4. A statistician measures the difference in songbird warble variation in 25 mockingbirds, both

before and after nutritional supplementation with Dr. Petit Oiseau’s Musical Bird Seed. Warble variation is determined by a cranky librarian, who characterizes the birds, before and after treatment, as one of the following “Lots of Notes There!” “Fair Variety,” and “Quite the Redundant Little Song.” What considerations determine choice of a test for this research? (Select all that apply.) a. The sample size is small to moderate. b. There is one group of birds, and all receive the treatment. c. A before-after type of design is used. d. The independent variable is nominal level. e. Birds are divided into two groups. f. The dependent variable is ordinal level. g. The dependent variable is ratio level. ANS: B, C, D, F

The independent variable, without the special bird seed versus with the special bird seed, has only two values, so it exists at the nominal level. The dependent variable has three possible values, and they represent ordered values, so it is an ordinal-level variable. This makes this research unsuitable for parametric tests. Since a nonparametric test will be used, sample size is not an issue. If the data address pre- and post-measurements in one group, or use two groups, but do not meet the assumptions involving normality or equal variances for an independent samples t-test, the nonparametric alternative is the Mann-Whitney U test. So number of groups, design type, and measurement levels of the independent and dependent variables determine the appropriate statistical test. How one interprets the results of these statistics depends on the design of the study. DIF: Cognitive Level: Analysis 5. A researcher designs a study to measure whether receiving a free season pass to a beautiful ski

resort near Bountiful, Utah, increases the number of days a subject who has lived in the area for 1 to 3 years skis during the season. An independent samples t-test of correlation is used to measure the effect of receiving a season pass upon number of ski days. If, instead, the researcher decided to measure the subjects’ responses by asking them to check one of these four replies on a survey, “Much more often than last year,” “More often than last year,” “Just about the same as last year,” or “Less often than last year,” why would the independent samples t-test have to be abandoned for a Mann-Whitney U test instead? (Select all that apply.) a. The variable of free season pass versus daily pay is measured at the nominal instead of the ratio level. b. The variable of free season pass versus daily pay is now measured at the ordinal instead of ratio level. c. The variable amount skied is now measured at the nominal level instead of the ratio level. d. The variable amount skied is now measured at the ordinal level instead of the ratio level. e. Both variables’ levels have changed. f. The independent samples t-test used demands ratio-level or interval-level data. g. The Mann-Whitney U test allows for ordinal level values, but not nominal. ANS: D, F, G

The independent variable has not changed and is still at the nominal level. The dependent variable is now measured at the ordinal level. The parametric statistics used to determine differences that are covered in this chapter are the independent samples t-test, paired or dependent samples t-test, and analysis of variance (ANOVA). If the data would ordinarily be appropriate for a t-test but do not meet the assumptions involving normality and/or equal variances, then the nonparametric alternative is the Mann-Whitney U test. DIF: Cognitive Level: Analysis 6. Which of the following are parametric statistical tests that may be used to measure, clarify, or

evaluate causation? (Select all that apply.) a. t-test for independent samples b. Mann-Whitney U test c. t-test for dependent samples d. Wilcoxon signed-rank test

e. f. g. h.

ANOVA Tukey Honestly Significant Difference (HSD) test Kruskal-Wallis test Chi-square

ANS: A, C, E, F

The parametric statistics used to determine differences that are covered in this chapter are the independent samples t-test, paired or dependent samples t-test, and analysis of variance (ANOVA). In addition, the Tukey Honestly Significant Difference test is a post hoc test used to clarify which variables are related, after an ANOVA shows a significant difference. The Mann-Whitney U test, Wilcoxon signed-rank test, Kruskal-Wallis test, and the chi-square are all nonparametric tests. DIF: Cognitive Level: Analysis 7. What are the principal reasons why a nonparametric test of causality is used instead of a

parametric one? (Select all that apply.) a. The assumptions for parametric analyses were not achieved. b. The effect that the interventional conditions produced was not measurable. c. The data were not normally distributed. d. The dependent variable was measured at the ordinal level. e. The results were not statistically significant. ANS: A, C, D

If the assumptions for parametric analyses are not achieved or if study data are at the ordinal level, then the nonparametric analyses of Mann-Whitney U, Wilcoxon signed-rank test, and Kruskal-Wallis H are appropriate techniques to use to test the researcher hypotheses. t-tests and ANOVA assume a normal distribution and measurement of the dependent variable at the interval/ratio level. DIF: Cognitive Level: Analysis 8. What do the t-test and the ANOVA have in common? (Select all that apply.) a. They both are used when the dependent variable is ordinal. b. They both assume a normal distribution. c. They both compare groups to decide whether they are the same or different. d. They both can be used when the dependent variable is of the interval level. e. They both require secondary post hoc analyses. f. They both use the same statistical tables for interpretation of results. g. They are both parametric analyses. ANS: B, C, D, G

The parametric statistics used to determine differences that are discussed in this chapter are the independent samples t-test, paired or dependent samples t-test, and analysis of variance (ANOVA). If the assumptions for parametric analyses are not achieved, or if study data are at the ordinal level, a nonparametric analysis must be used instead. Post hoc tests have been developed specifically to determine the location of group differences after ANOVA is performed on data from more than two groups. The t distribution table is used for comparison of calculated t-values. The F distribution table is used for comparison of calculated ANOVA values.

DIF: Cognitive Level: Application 9. Which of the following results would represent statistical significance, if the level of

significance were set at 0.05 for each? (Select all that apply.) a. t = 8.43, p < 0.01 b. X2 = 10.83, p < 0.1 c. F = 2.37, p < 0.07 d. r = 0.2, p = 0.23 e. rs = 0.74, p = 0.049 ANS: A, E

The obtained result from the calculation of the statistic is compared with the appropriate table, at the level of significance set by the researcher at the outset of the study. In this case, the level of significance has been set at 0.05. By this criterion, the two statistically significant values listed are p < 0.01 and p = 0.049. The other three are too large. DIF: Cognitive Level: Analysis

Chapter 26: Interpreting Research Outcomes Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A researcher studies the effect on reading comprehension level of providing fourth-grade boys

who are slow and ponderous readers with illustrated comic books for a 6-week summer session instead of textbooks, hypothesizing that reading associated with pictures will result in a higher reading comprehension level. The researcher sets the level of significance at p < 0.05. Analysis of the data indicates that there was a significant difference between the two groups, which were randomly selected and composed of 100 subjects each. However, the experimental comic book group’s scores improved less than did the scores of the boys who used the textbooks. The measured p-level was 0.026. What type of finding is this? a. Significant results that are in keeping with those by the researcher b. Nonsignificant results c. Significant results that oppose those predicted by the researcher d. Mixed results ANS: C

Significant results that are the opposite of those predicted, if the results are valid, are an important addition to the body of knowledge. These are sometimes referred to as “unexpected results.” Such results, when verified by other studies, indicate that the theory being tested needs modification and refinement. Because these types of studies can affect nursing practice, this information is important. DIF: Cognitive Level: Application 2. The analysis of the data from a study indicates that there was a significant difference between

two groups, which were randomly selected and composed of 300 subjects each. The instruments measuring stress, mood, and various scaled measures of emotion were well normed, widely tested, and suitable. The researcher begins interpretation of the data and discovers that during data collection one of the assistants had recorded the demographic item “household size” incorrectly for 25 subjects, understanding the item as “number of people who live with you.” The researcher makes a decision to work with the data that are recorded for this variable, treating the faulty entries as missing values. How should the researcher present this information in the discussion section of the report? a. As a statistical conclusion validity limitation b. As a serendipitous finding c. As a construct validity limitation d. It is unnecessary to present this information in the report because the researcher is allowed to clean the data in this way. ANS: C

Limitations of a study may include the scope and its methodology, but are essentially, validity-based limitations to generalizations of the findings. It is critical for the development of science and evidence-based practice that limitations are acknowledged. There are four elements of design validity: construct validity, internal validity, external validity, and statistical conclusion validity. Construct validity issues involve whether or not a central study concept was operationalized, or made measurable, in the way that best represented the concept’s presence or range of values. Construct validity may be due to faulty reasoning that occurs when the researcher selects measurements for study variables. For purposes of writing the Discussion section, instrument validity is considered a subtype of construct validity, because it reflects operationalization of variables. If the validity of an instrument is poor, this is a construct validity issue: the instrument did not measure what it was intended to measure. Statistical conclusion validity is affected by errors that occur during the processes of data management and analysis. Choosing the correct statistical test is critical during the planning of the study, and consultation with a biostatistician is recommended. Continuing consultation with the biostatistician during data analysis is also recommended to ensure that the data meet the assumptions of the selected tests and missing data are handled appropriately. Before analyzing the data, the researcher should clean the data by identifying all missing data points and determining whether the information can be obtained and entered into the data file. If a large number of subjects have missing data on specific variables, the researcher needs to make a judgment regarding the availability of sufficient data to perform analysis with those variables. In some cases, subjects must be excluded from the analysis because of missing essential data. Another possibility is that the researcher considers taking data at one level of measurement and converting it to a lower level of measurement. Serendipitous results are discoveries or researcher observations that were not the focus of the study. DIF: Cognitive Level: Synthesis 3. In a cross-sectional study, a researcher studies career trajectories in nurses over the past 20

years. There are five correlational research hypotheses. Why are mixed results, related to significance of findings, to be expected? a. The study is cross-sectional, and the economy has made bedside care a more practical decision, over the past few years. b. Groups across time cannot be expected to have the same responses to career advancement. c. The study is merely correlational. d. Five statistical hypotheses are being tested; not all of these can be expected to demonstrate statistical significance. ANS: D

Mixed results are probably the most common outcome of studies that examine more than one relationship. In this case, one variable may uphold the characteristics predicted, whereas another does not, or two dependent measures of the same variable may show opposite results. DIF: Cognitive Level: Analysis 4. A researcher working for a company that produces a standardized examination that predicts

whether or not nursing students will pass the national licensure examination tests this tool at a level of significance of  = 0.01, with power = 0.91. The results are statistically significant. What interpretation can the researcher justifiably make? a. Findings are important to nursing schools and valuable for them.

b. The examination should be used by all nursing schools. c. There is good evidence that the results can be replicated, with similar results. d. Results will be the same if the study is repeated with another sample. ANS: C

The researcher chooses the probability of making a Type I error when setting á, the level of significance. In nursing research, a is usually set at 0.05, meaning that the researcher will allow a 5% or lower chance of making a Type I error. A level of significance of p < 0.01 is much more stringent and decreases the possibility of error to 1%. For the researcher to have achieved statistical significance at such a stringent a with power of 0.91, the sample had to have been quite large. Significant results that coincide with the researcher’s predictions validate the proposed logical links among the elements of a study. These results support the logical links developed by the researcher among the purpose, framework, questions, variables, and measurement methods. There is good evidence that the reports are reproducible. DIF: Cognitive Level: Analysis 5. Which interpretation of correlational study results is acceptable as worded? a. The study proved that cigarette smoking causes lung cancer. Financial incentives

must be offered by insurance companies to all persons who cease smoking. b. Findings suggest that antihypertensives influence both length and quality of life

and that their use is more beneficial than formerly realized. c. The positive correlation between owning a dog who demands to be walked daily

and the owner’s cardiovascular health indicates that all people should own dogs. d. Results imply that all humans who use amphetamines will have shortened life

spans, and patient teaching needs to include this vital information. ANS: B

Implications of research findings for nursing are the meanings of the results for the body of nursing practice and knowledge. Implications for practices are often based, in part, on whether treatment decisions or outcomes would be different in view of the study findings. Only option B indicates the tentative nature of the findings from a single study. Although a significant finding is very gratifying, the researcher needs to consider alternative explanations for the positive findings. When forming conclusions, it is important to remember that research never proves anything; rather, research offers support for a position. Proof is a logical part of deductive reasoning, but not of the research process. Especially with correlational research, alternative (rival) hypotheses abound. DIF: Cognitive Level: Analysis 6. A researcher studies the effect upon pain control of providing pet therapy for children on a

pediatric ward. While conducting the study, the researcher becomes aware of a strong correlation between parental presence and hours of children’s sleep. What is this correlation? a. The ability to consent far more subjects than were originally projected: a lucky occurrence b. Relationships between variables that were not hypothesized or predicted from the framework: serendipitous finding c. The identification of a variable that affects the dependent variable and distorts its value: extraneous variable d. A condition that affects generalization: limitation

ANS: B

Serendipitous results are discoveries or researcher observations that were not the focus of the study. Most researchers examine as many elements of data as possible in addition to those directed by the research objectives, questions, or hypotheses. In doing so, they sometimes discover a relationship or variable distribution heretofore unearthed. Serendipitous results should be reported, because they are legitimate discoveries of the study. DIF: Cognitive Level: Analysis 7. A researcher summarizes the findings and then makes generalizations. Why does the

researcher refer to the literature before making generalizations? a. If the current study is a replication of previous research, its generalizations will be identical to those of the study it replicates. b. If there is no previous research in this area, no generalizations can be made. c. If the current study is the second by this researcher, its generalizations will be to the population from which the second sample was drawn and will specifically exclude the sample from the first study. d. If there is a lone study in this area, generalizations are narrow; if there is previous research of a parallel nature, more widespread generalization is in order. ANS: D

Generalization extends the implications of the findings from the sample studied to a larger population or from the situation studied to a larger situation, within the limitations imposed by design validity issues. Generalizations apply to the current study findings, in conjunction with previous studies in the same area. Generalizations like these, based on accumulated evidence from many studies, are called empirical generalizations. These generalizations are important for verifying hypotheses and theoretical statements and can contribute to the development of new theories. Empirical generalizations are foundational to scientific discovery and, within nursing, provide a basis for generating evidence-based guidelines to manage specific practice problems. DIF: Cognitive Level: Analysis 8. A researcher makes a statement near the end of a research article, stating that the findings

contribute to nursing’s body of knowledge and they also provide evidence that the intervention may be helpful in the population from which the sample was drawn. What does this comment address? a. Serendipitous findings b. Implications c. Generalizations d. Limitations ANS: B

Implications of research findings for nursing are the meanings of the results for the body of nursing practice and knowledge. As with generalizations, implications for practice can be summative, including both the current study and related literature in the same area as evidence. Implications for practices are often based, in part, on whether treatment decisions or outcomes would be different in view of the study findings. In terms of practice, implications can be drawn from any part of the study findings, descriptive or inferential, but they must arise from those findings not from general principles of nursing practice. Generalization extends the implications of the findings from the sample studied to a larger population or from the situation studied to a larger situation, within the limitations imposed by design validity issues. Serendipitous results are discoveries or researcher observations that were not the focus of the study. Limitations of a study may include the scope and methodology, but are essentially validity-based limitations to generalizations of the findings. DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. The analysis of the data from a study indicates that there was a significant difference between

the two groups, which were randomly selected and composed of 100 subjects each. The instruments measuring stress, mood, and various scaled measures of emotion were well normed, widely tested, and suitable. As the researcher begins interpretation of the data, the researcher discovers that during data collection, one of the assistants had recorded the demographic item “household size” incorrectly, understanding the item as “number of people who live with you.” The original paper surveys are still available, and the ones this particular assistant collected are all clearly marked with the assistant’s initial on each page. How can this data item be “saved”? (Select all that apply.) a. Erroneous values can be identified and eliminated from the data analysis for this single item. b. Erroneous values can be located and reentered as the true values, since the systematic error has been identified, quantified, and attributed. c. Data analysis may proceed and the error noted in the final report as a methodological limitation. d. An overlapping ordinal measurement can be used, in which the categories are 0-1, 1-2, 2-3, and so forth. e. The data may be analyzed as a nominal variable and so coded. ANS: A, B

Limitations of a study may include the scope and its methodology, but are essentially validity-based limitations to generalizations of the findings. There are four elements of design validity: construct validity, internal validity, external validity, and statistical conclusion validity. Methodological limitations may result from factors such as poor operationalization of variables, a confounding variable, a sample that was inexplicably nonrepresentative, uncontrolled-for and unmeasured extraneous variables, and use of inappropriate statistical analysis. Nominal level of measurement is the lowest of the four measurement levels or categories. It is used when data can be organized into categories of a defined property but the categories cannot be ordered. Data that can be measured at the ordinal level can be assigned to categories of an attribute that can be ranked. To be meaningful, measurements must be mutually exclusive. Changing the data to a nominal or ordinal measurement will not “save” the item. Reporting the item as erroneous does not “save” the item.

DIF: Cognitive Level: Synthesis 2. A researcher has conducted a study that uses a measurement tool for agitation, normed in a

hospital setting, in an outpatient mental health setting. After completion of the data analysis phase, which of the following is the next logical step in evaluating the evidence? (Select all that apply.) a. Recalibration of all instruments used for physiological measurements b. Review of the literature c. Identification of statistically significant findings d. Examination of the measurement tool’s reliability in this setting e. Reevaluation of the tool’s validity in this population ANS: D, E

Limitations of a study may include the scope and its methodology, but are essentially validity-based limitations to generalizations of the findings. There are four elements of design validity: construct validity, internal validity, external validity, and statistical conclusion validity. Each of type of validity should be examined upon before writing the Discussion portion of a research report. Construct validity issues involve whether or not a central study concept was operationalized, or made measurable, in the way that best represented the concept’s presence or range of values. For purposes of writing the Discussion section, instrument validity is considered a subtype of construct validity, because it reflects operationalization of variables. If the validity of an instrument is poor, this is a construct validity issue: the instrument did not measure what it was intended to measure. If the reliability of an instrument is poor, a different problem is present: the instrument’s exact values cannot be trusted. However, when the range of error of an instrument can be determined, meaningful statistical analysis based on broad categories of value instead of exact values is still possible. DIF: Cognitive Level: Application 3. A researcher studies the effect of a computerized hospital charting system on nurses’

compliance with charting the exact times of tracheostomy care, periodic turning of patients, and bed baths. The researcher hypothesizes that instituting the new charting system would improve compliance. The sample size is 120. The level of significance is set at 0.05 and the power at 80%. Findings are nonsignificant, at p = 0.146. How might this be discussed by the researcher? (Select all that apply.) a. The null hypothesis was accepted. There was no difference in compliance when paper charting was replaced with computer charting, in terms of the variables of tracheostomy care, periodic turning, and bed bath charting. b. Nurses do not chart consistently the tracheostomy care, periodic turning, and bed baths they deliver, regardless of charting system. c. The effect size was smaller than expected; a repeat power analysis revealed that the sample size of 120 was insufficient to demonstrate a significant difference. d. This study showed no significant difference between the two charting methods, in terms of compliance. e. Had the level of significance been set at 0.15, the findings would have reached statistical significance. ANS: A, C, D, E

Unpredicted nonsignificant or inconclusive results are often referred to as negative results. The negative results could be a true reflection of reality. In this case, the reasoning of the researcher or the theory used by the researcher to develop the hypothesis is in error, but the study was scientifically sound. If so, the negative findings are an important addition to the body of knowledge. With nonsignificant results, it is important to determine if adequate power of 0.8 or higher was achieved for the data analysis. The researcher needs to conduct a power analysis to determine if the sample size was adequate to prevent the risk of a Type II error. A Type II error means that in reality the findings are significant, but because the sample size was inadequate, statistical tests failed to show significance. Negative results do not mean that there are no relationships among the variables or differences between groups; they indicate that the study failed to find any relationships or differences. DIF: Cognitive Level: Application 4. A nurse manager in a trauma intensive care unit conducts a quality improvement evaluation

project. During this process, the manager discovers that patients with adult respiratory distress syndrome almost always have better outcomes when they are placed in the five beds located furthest away from the nursing station. Examining the data, the manager discovers that the room doors in these five rooms are consistently half-closed or three-quarters closed. In addition, nurses have been documenting that these patients sleep more than the other 10 patients on the unit. What are the nurse manager’s options for generalizing the findings? (Select all that apply.) a. There is no practical use for this research; no generalization is appropriate. b. Findings should be generalized immediately, and in print. These are important findings. c. The nurse can present the findings at conferences, but generalization is limited to the hospital in which the data were collected. d. The nurse manager can obtain permission from an institutional review board to conduct a formal research study, in order to formally test hypotheses, and then generalize the findings of this second study. e. Arrangements should be made immediately on the unit to keep all patients’ doors half-closed or three-quarters closed. ANS: C, D

Limitations of a study may include the scope and its methodology, but are essentially, validity-based limitations to generalizations of the findings. There are four elements of design validity: construct validity, internal validity, external validity, and statistical conclusion validity. Limitations may result from factors such as poor operationalization of variables, a confounding variable, a sample that was inexplicably nonrepresentative, uncontrolled-for and unmeasured extraneous variables, or use of inappropriate statistical analysis. DIF: Cognitive Level: Analysis 5. If, after power analysis, a researcher’s interventional study findings are nonsignificant, what

might this imply? (Select all that apply.) a. The effect size was smaller than originally expected. b. The effect size was larger than originally expected. c. The operational definition of the independent variable was faulty. d. The operational definition of the dependent variable was faulty. e. A Type I error occurred.

f. A Type II error occurred. g. The intervention was not an effective one. ANS: A, C, D, F, G

Negative results could be due to poor operationalization of variables, a confounding variable, a sample that was inexplicably nonrepresentative, uncontrolled-for and unmeasured extraneous variables, use of inappropriate statistical techniques, or faulty analysis. Negative results, in any case, do not mean that there are no relationships among the variables or differences between groups; they indicate that the study failed to find any relationships or differences. The sample size was initially judged to have been adequate enough to prevent the risk of a Type II error, based on initial calculations, but if the effect size was very small, a Type II error might have occurred. The negative results could be a true reflection of reality. In this case, the reasoning of the researcher or the theory used by the researcher to develop the hypothesis is in error. DIF: Cognitive Level: Evaluation 6. In interpreting the findings of a study, the researcher should do which of the following?

(Select all that apply.) a. Discuss the findings, with respect to clinical implications. b. Boldly and fearlessly identify the limitations of the study. c. Make cautious and well-founded conclusions, based on the findings. d. Based on the existing literature, plus this study, recommend further research. e. Make excuses for limitations. f. Relate findings back to the purpose and framework of the study. g. Generalize broadly. ANS: A, B, C, D, F

Interpretation includes several intellectual activities, such as examining evidence, forming conclusions, identifying study limitations, generalizing the findings, considering implications, and suggesting further research. Generalization extends the implications of the findings from the sample studied to a larger situation, within the limitations imposed by design validity issues was drawn, and should be based on accumulated evidence from many studies. Excuses should not be made. DIF: Cognitive Level: Analysis 7. How are markedly negative results of a multi-site interventional nursing study with a huge

sample and stringent level of significance helpful? (Select all that apply.) a. They rule out the usefulness of the intervention for all clients. b. They provide evidence that may change clinical practice, if the intervention is currently being applied in practice to all healthcare clients. c. They contribute to the total body of nursing knowledge. d. They may indicate different directions for theoretical ideas. e. They establish the fact that the intervention is not universally effective with all clients. f. They allow only cautious generalization. ANS: B, C, D, E

servings of freshly pressed tomato juice for prevention of cancers of the gastrointestinal tract. The results were statistically significant at the p < 0.01 level. During interpretation, which of the following will the researcher employ? (Select all that apply.) a. Examination of the results, in comparison with similar literature about fresh tomatoes and cancer, to decide whether the sum of all knowledge constitutes sufficient evidence for widespread generalization b. Exploration of the clinical significance of the findings, as opposed to the statistical significance c. Initiation of discussions with manufacturers of juice machines, so as to take advantage of the anticipated increase in sales d. Formation of some sort of conclusions, relative to the study findings and related literature e. Promulgation of the results to the popular media, so that as many people as possible in the world can advantage themselves of the intervention f. Recommendations for further studies on fresh tomato juice and its effects on health g. Consideration of implications related to nursing’s body of knowledge ANS: A, B, D, F, G

Interpretation of research outcomes requires reflection upon three general aspects of the research and their interactions: the primary findings, validity issues, and the resultant body of knowledge in the area of investigation. These issues will determine how the researcher writes the Discussion section of the research report, presenting the findings, limitations, conclusions, generalizations, usefulness of the research, and recommendations for subsequent inquiry in the area. DIF: Cognitive Level: Application 9. The U.S. census is an example of a huge descriptive research project that uses the entire

population as the sample. What are some of the limitations of generalizing census findings back to the entire population? (Select all that apply.) a. Although all homes must fill out a census report, the homeless population often cannot be accessed, surveyed, and counted, so the homeless population is underrepresented in the findings. b. Persons whose primary language is something other than English or Spanish, and who do not speak either language, are more likely to be missed in the census. c. The survey method of data collection relies on self-report; some misrepresentation or error is inevitable. d. The population changes continuously, and the one described in the census isn’t very much like the population on the day the results are published. e. Persons in the United States who are no longer here legally but plan to stay do not

fill out a report. ANS: A, B, C, E

The limitations of a study need to be clearly identified and discussed in relation to the study conclusions. Limitations of a study may include the scope and its methodology, but are essentially, validity-based limitations to generalizations of the findings. There are four elements of design validity: construct validity, internal validity, external validity, and statistical conclusion validity. Limitations may result from factors such as poor operationalization of variables, a confounding variable, a sample that was inexplicably nonrepresentative, uncontrolled-for and unmeasured extraneous variables, or use of inappropriate statistical analysis. DIF: Cognitive Level: Analysis 10. Choose which of the following limitations are not related to construct validity, in a study of

home UV treatment of depressive illnesses. (Select all that apply.) a. An interventional study has a 60% attrition rate. b. The operational definitions are not in line with the conceptual definitions. c. The study framework is related to the social costs of depressive illness. d. The subjects excluded from participation in a study of depressive illness and UV home treatment were those who had been hospitalized in the past for depression. e. The multi-site study examining UV home treatment and depressive illness is conducted only in major west coast urban centers. ANS: A, D, E

Limitations of a study may include the scope and its methodology, but are essentially validity-based limitations to generalizations of the findings. The limitations of a study might be theoretical or methodological and need to be clearly identified and discussed in relation to the study conclusions. External validity is the extent to which study results are generalizable to the target population. External validity is strongest for studies with large, randomly selected samples, and it is still stronger when that sample is drawn from many different sites. Studies can be generalized to the population from which the sample was drawn; a sample drawn from one geographic area can, in general, be generalized back only to that area. Sometimes a study might yield a smaller-than-expected sample size due to attrition. If so, the effect of a smaller sample on the power of planned statistical analyses must be considered because this smaller sample may be inadequate to test the study’s hypotheses. Large attrition rates affect both external validity and, potentially, internal validity. DIF: Cognitive Level: Analysis

Chapter 27: Disseminating Research Findings Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. A graduate student states, in a master’s thesis, that “despite public awareness programs to

educate the public about the safety of pediatric immunizations, a staunch core of highly educated and well-informed parents continues to attribute the rise in childhood autism to vaccination. Because of this, recent efforts have been brought to bear in the qualitative arena, attempting to identify and isolate factoids and half-truths that perpetuate the myth. Nonetheless, mostly because belief structures appear bound by geography, not enough is known about reasons that some clusters of parents postpone or avoid vaccination.” The quotation is an example of a(n) ___________ and appears in the ____________ section of the research report. a. objective; Methods b. purpose statement; Introduction c. problem statement; Introduction d. literature review; Results ANS: C

The research problem statement focuses on the principal concepts upon which the study will focus and contains certain essentials. The first of those essentials is a general summary of what is now about the phenomenon of interest, followed by a sentence that identifies a research gap. The introduction of a research report discusses the background and significance of the problem, so as to inform the reader of why the study was conducted. Statements are supported with citations from the literature. The introduction may also describe the study framework or philosophical perspective and identify the research purpose (aims, objectives, questions, or hypotheses if applicable). DIF: Cognitive Level: Application 2. Prior to conducting a grounded theory study, in which 11 women undergoing radiation for

If the research project included a pilot study, the researcher describes the reason for the pilot, its implementation, and its results succinctly. Any changes made in the research project based on the pilot study should also be described. DIF: Cognitive Level: Application

3. Prior to conducting a grounded theory study, in which 11 women undergoing radiation for

breast cancer were interviewed multiple times, the researchers conducted a pilot study in which they interviewed three women every 2 weeks from the time radiation was planned until 4 weeks after it was completed. The purpose for the pilot study was to refine the interview instrument and to discover whether women would be willing to be interviewed this frequently about such a private topic. The pilot was not published separately. In the institutional review board application, the researcher indicated an intent to include information in the research report about the three women in the pilot study—what going through the process of radiation therapy was like for them—in addition to the 11 main study women. In this case, if the findings from the women in the pilot were not included in the Methods section, where would the information about the process of going through radiation therapy obtained from the pilot study women be included? a. Introduction b. Results c. Discussion d. Appendix ANS: B

If the research project included a pilot study, the researcher describes the reason for the pilot, its implementation, and its results succinctly. The researcher should also describe any changes made in the research project based on the pilot study and mention whether pilot data were or were not included in the analysis of results. However, data analysis in qualitative research occurs concurrently with data collection. In addition, analysis of data from an interview may result in the researcher asking an additional question in subsequent interviews to confirm or not confirm an initial interpretation of the data. Because of this, information related to the phenomenon and obtained in the pilot phase may be included in the Results section. DIF: Cognitive Level: Application 4. “All subjects were asked whether they would be willing to participate in this descriptive

study, while they waited to be seen by a gastroenterologist, prior to their initial colonoscopies. They were given basic information about the research, and told that participation was strictly voluntary, according to guidelines from the Institutional Review Board (IRB) for the clinics and hospital. The research had been approved as minimal risk by the IRB. All 31 subjects were asked to participate agreed to do so.” The researcher should include information about this process in which section of the manuscript? a. Abstract b. Introduction c. Methods d. Appendix ANS: C

The Methods section of a research report describes how the study was conducted. This section needs to be concise, yet provide sufficient detail for nurses to appraise critically or replicate the study procedures. In this section, the researcher will describe the study design, sample, setting, data collection tools and process, and plan for data analysis. This section of the research report should describe the sampling method, criteria for selecting the sample, sample size, and sample characteristics. Details about subject recruitment, including refusal or acceptance rates, should be reported.

DIF: Cognitive Level: Application 5. “Lazarus’ coping paradigm suggests that it is the appraisal of a stressor as potentially harmful

that begins the avoidance cascade. Thomason further characterized adaptation to management of chemotherapy symptomatology as mere reflections of a primary appraisal of potential harm, providing a set point for intensity of reactions. We used these conceptual connections to formulate testable assumptions for this study.” Where in the research report would this quotation be located? a. Introduction b. Methods c. Results d. Discussion ANS: A

The introduction of a research report discusses the background and significance of the problem so as to inform the reader of why the study was conducted. Statements are supported with citations from the literature. The introduction may also describe the study framework or philosophical perspective and identify the research purpose (aims, objectives, questions, or hypotheses if applicable). The study aim or purpose and specific research questions flow from the phenomenon or research problem, clarify the study focus, and identify expected outcomes of the investigation. DIF: Cognitive Level: Application 6. “Thomason’s set-point theorizations explain, in part, why patients in chemotherapy who

reported high levels of apprehension and anxiety prior to initiation invariably reported more severe average symptomatology levels. In addition, their symptoms were ameliorated less completely by standard therapeutic interventions, such as antiemetics and soporifics.” Where in the research report would this quotation be located? a. Introduction b. Methods c. Results d. Discussion ANS: D

The Discussion section ties the other sections of the research report together by connecting parts of the report with one another. It includes the major findings, limitations of the study, conclusions drawn from the findings, implications of the findings for nursing, and recommendations for further research. Findings should be discussed in relation to the overriding theoretical framework as well as the research problem, purpose, and questions or hypotheses. DIF: Cognitive Level: Application 7. What part of the research report names the study design? a. Introduction b. Methods c. Results d. Discussion

ANS: B

The Methods section of a research report describes how the study was conducted. In this section, the researcher will describe the study design, sample, setting, data collection tools and process, and plan for data analysis. DIF: Cognitive Level: Comprehension 8. The results of an applied research study for anxiety management in children were published in

both a highly respected nursing research journal and in a second journal specific to pediatrics that focuses on practice issues. The first article contained detailed statistical analyses and discussions of the results, as an extension of the author’s previous basic research. The second presented the research in much simpler language, providing pictures of the children and discussing nursing practice applications. Why does this or does this not represent duplicate publication? a. It does represent duplicate publication because both articles reported results of the same study. b. It does not represent duplicate publication because the language was completely different in the two articles, and the journal audience was different. c. It does represent duplicate publication because the second article was a paraphrase of the first. d. It does not represent duplicate publication because the second article referenced the first and focused heavily on practice applications, not included in the first. ANS: D

procedure room for all painful procedures including IV starts, a master’s student lists the four principal study findings, one by one, following each with an explanation of how each finding contributes to nursing knowledge. The major thesis advisor directs the student to fix this in the second draft of the thesis. Why does the thesis advisor require this? a. This entire segment of the thesis should appear in the Discussion section. The Results section contains all of the study findings, with detailed statistics on each. b. A thesis should not explain how its findings contribute to nursing knowledge. c. This is applied research. Its findings should apply only to practice. d. Findings appear in the Results section, which includes only facts and nothing else. The explanation part of the above must be placed in the Discussion section. ANS: A

The Results section usually begins with a description of the sample and subgroups, if applicable, followed by what was learned from the study. For each research objective, question, or hypothesis, the results generated from the analyses are provided. The Discussion section ties the other sections of the research report together by connecting parts of the report with one another. It includes the major findings, limitations of the study, conclusions drawn from the findings, implications of the findings for nursing, and recommendations for further research. Findings should be discussed in relation to the overriding theoretical framework as well as the research problem, purpose, and questions or hypotheses.

DIF: Cognitive Level: Application MULTIPLE RESPONSE 1. In which parts of the research report could the reader find the one most important result of the

study? (Select all that apply.) a. Abstract b. Introduction c. Methods d. Table 1 e. Results f. Discussion g. References h. Appendix ANS: A, E, F

The abstract of a study summarizes the key aspects of the study in 100 to 300 words and is the first component of a research report. Structured abstracts have specific headings such as problem, purpose, framework, methods, sample size, key results, and conclusions. The Results section usually begins with a description of the sample and subgroups, if applicable, followed by what was learned from the study. For each research objective, question, or hypothesis, the results generated from the analyses are provided. The Discussion section ties the other sections of the research report together by connecting parts of the report with one another. It includes the major findings, limitations of the study, conclusions drawn from the findings, implications of the findings for nursing, and recommendations for further research. The introduction of a research report discusses the background and significance of the problem so as to inform the reader of why the study was conducted. Statements are supported with citations from the literature. The introduction may also describe the study framework or philosophical perspective and identify the research purpose (aims, objectives, questions, or hypotheses if applicable). The Methods section of a research report describes how the study was conducted. In this section, the researcher will describe the study design, sample, setting, data collection tools and process, and plan for data analysis. Table 1 in a research report commonly presents characteristics of the study sample, with a note at the foot of the table stating, “Differences among groups were found not to be statistically significant,” this represents a post hoc analysis for the distribution of potentially extraneous demographic variables. The final section of the research report is the reference list, which includes all sources that were cited in the report. When data collection tools are used in qualitative research, such as observation guides, initial questions for open-ended interviews, or forms to record extracted facts from historical documents, they are described and a copy provided in the report as an inset or as an appendix. DIF: Cognitive Level: Synthesis 2. There was a research gap before the study was performed. The study results filled the research

gap. In what part of the research report would the research gap be identified? In what part of the research report would the researcher’s strategy for filling the research gap be reported? (Select all that apply.) a. Abstract ... References b. Abstract ... Abstract

c. d. e. f. g. h.

Introduction ... Discussion Introduction ... Methods Abstract ... Methods Methods ... Methods Results ... Discussion Introduction ... Discussion

ANS: D, E

(Select all that apply.) a. Abstract b. Introduction c. Methods d. Results e. Discussion ANS: A, E

The abstract of a study summarizes the key aspects of the study in 100 to 300 words and is the first component of a research report. Structured abstracts have specific headings such as problem, purpose, framework, methods, sample size, key results, and conclusions. Conclusions can include potential applications for practice. The Discussion section ties the other sections of the research report together by connecting parts of the report with one another. It includes major findings, limitations of the study, conclusions drawn from the findings, implications of the findings for nursing, and recommendations for further research. The introduction of a research report discusses the background and significance of the problem, so as to inform the reader of why the study was conducted. The introduction may also describe the study framework or philosophical perspective and identify the research purpose (aims, objectives, questions, or hypotheses if applicable). The Methods section of a research report describes how the study was conducted. In this section, the researcher will describe the study design, sample, setting, data collection tools and process, and plan for data analysis. The Results section usually begins with a description of the sample and subgroups, if applicable, followed by what was learned from the study. For each research objective, question, or hypothesis, the results generated from the analyses are provided. The Discussion section ties the other sections of the research report together by connecting parts of the report with one another. It includes the major findings, limitations of the study, conclusions drawn from the findings, implications of the findings for nursing, and recommendations for further research. DIF: Cognitive Level: Synthesis 4. A master’s thesis uses Husserlian phenomenology as its method. In the research report, the

student has mentioned the method by name and has adhered to all of the tenets of that method. The thesis advisor requires the student to include in the thesis a 2- to 5-page summary of the philosophy of Husserlian phenomenology. Why does the thesis advisor require this? (Select all that apply.) a. The thesis advisor is not familiar with the method and cannot evaluate the thesis without this information. b. It is important that the thesis makes clear what Husserlian phenomenology implies, relative to the researcher’s part in data collection and data analysis. c. Several assumptions of the thesis may emanate from Husserlian phenomenology, and they should be consistent with its philosophy. d. The reader of the thesis, and publications emanating from it, may not be clear as to what Husserlian phenomenology is. An explanation is in order. e. The reader can follow the analysis better when the method is better understood. f. The philosophy that underlies qualitative research is, in essence, the study’s theoretical framework. A framework should include a summary of its main points. ANS: B, C, D, E, F

The philosophical perspective of the researcher guides the questions asked and the methods selected for conducting a specific study. Both quantitative and qualitative researchers have philosophical perspectives. Qualitative studies are based on a wide range of philosophies, such as phenomenology, symbolic interactionism, and hermeneutics, each of which espouses slightly different approaches to gaining new knowledge. Most qualitative researchers do not identify specific theoretical frameworks during the design of their studies, as is expected for quantitative studies. The concern is that designing a study in the context of a theory will influence the researcher’s thinking and result in findings that are meaningful in the theoretical context, but may not be true to the participants’ perspectives on the topic. However, the philosophical bases for the various approaches to qualitative studies provide theoretical grounding for qualitative studies without predisposing the data analysis to a single interpretation; the philosophy is the study’s theoretical framework. As such, it deserves a few pages of exposition to aid the reader’s understanding. The Methods section for a qualitative study includes the specific qualitative design (e.g., phenomenology, grounded theory, or ethnography), a detailed description of the data collection method such as interview or observation, and the data management and analysis plan. In the presentation of the qualitative approach, the researcher provides the philosophical basis for and the assumptions of the qualitative method with citations from the primary sources. In addition, a rationale for selecting this type of qualitative study is needed. DIF: Cognitive Level: Synthesis 5. A researcher presents the results of a recent research project at several conferences. Duplicate

publications are not acceptable and represent self-plagiarism, but duplicate presentations seem valued. Which of the following facts explains this? (Select all that apply.) a. Duplicate conference presentations are valued only when they occur in widely separated geographic areas. b. Questions and comments from conference audiences can contribute to the researcher’s ongoing analysis and inspire new analyses of data. c. If similar research by the same author is ongoing, each conference presentation can include new insights and interpretations, reflecting work in progress. d. Reaching a broad audience necessitates presentation at several conferences. e. Self-plagiarism is a term that refers to the printed word, not to conference presentations. f. If a researcher submits a different abstract to each conference that publishes printed conference abstracts, there is no self-plagiarism. ANS: B, C, D, E, F

Duplicate publication is the practice of publishing the same article or major portions of the article in two or more print or electronic media without notifying the editors and copyright holders or referencing the other publication in the reference list. Duplicate publication does not refer to oral presentations. However, if portions of an article have been presented at a scientific meeting in the form of an oral podium or poster presentation, this should be acknowledged along with funding sources and any potential conflict of interest. DIF: Cognitive Level: Analysis 6. Which of the following are considered poor scholarly writing and, consequently, should not

appear in a published research report? (Select all that apply.) a. “Subjects who could not decide whether to select A, B, or C as item options were

b. c. d. e. f. g. h.

instructed to leave the item blank.” “Regardless of amount of the independent variable of electricity that was applied, dependent variable changes were negligible thus indicating lack of causation.” “Any subject desiring to retract their permission for the study had his or her name removed from the master list.” “Erstwhile subjects had little insight into the retained fragments of their sublimated ignoscency.” “Subjects A and B completed the trial in half the time taken by other subjects, without caffeine enhancement. Hah!” “Subject attrition was nil. Not one person dropped out of the study, even in progress. Except the ones we kicked out, of course.” “Subject’s responses were markedly different across groups.” “The intervention group was expected to document symptoms at least daily, using a journal. Twice-daily documentation was encouraged.”

ANS: B, C, D, E, F, G

A quality research report has no errors in punctuation, spelling, or sentence structure. It is also important to avoid confusing words, clichés, jargon, excessive wordiness, and abbreviations. Word processing programs have “tools” commands that have the capacity to proofread manuscripts for errors. DIF: Cognitive Level: Synthesis 7. Which of the following represent poor scholarly writing and, consequently, should not appear

as they are written in a journal article? (Select all that apply.) a. “Regretfully nobody in the control group survived past three years this is because of the continued effects of the disease process itself if untreated it is fatal.” b. “Results of the study indicated that causation was directional in the A, B, F, and K groups however none were identified as impacting the final outcome.” c. “We as experienced researchers cannot explain why the intervention failed in not one, but three consecutive mini-trails, numbers 5, 6, and 7, becoming suddenly effective in the subsequent twenty-three mini-trials. We checked and rechecked instrument calibrations, controlled diligently for intra-rater reliability, recomputed coefficients of change, trended all data, reentered data manually, examined the effect of sixteen potentially extraneous variables, and ultimately ended as baffled as we started.” d. “The result’s were a complete surprise. 44% of the control subject’s experienced spontaneous remission’s.” e. “Attrition continued over the course of the experiment, with additive attrition of 2% in the first quarter, 5% in the second quarter, 16% in the third quarter, and 25% in the fourth. In the second year, attrition claimed another half of the sample. Data collection was suspended after the eighth quarter, since the results had limited applicability, due to extensive attrition.” f. “An inadequate sample threatened to end the study. Inclusion criteria were broadened, to include those who had participated in clinical research, in the past, but there were no takers.” g. “There was no way of determining who’s answers had been positive on the pre-test, until the post-test was completed.” ANS: A, B, C, D, F, G

A quality research report has no errors in punctuation, spelling, or sentence structure. It is also important to avoid confusing words, clichés, jargon, excessive wordiness, and abbreviations. Word processing programs have “tools” commands that have the capacity to proofread manuscripts for errors. DIF: Cognitive Level: Synthesis 8. There are several steps in the process of converting a master’s thesis into a publishable article:

selecting a journal, writing a query letter, preparing an original manuscript, submitting the manuscript for review, and performing the revisions the editor indicates. Why should preparation of the manuscript not occur first? (Select all that apply.) a. It would be foolish to write a manuscript without knowing the maximum length of manuscript that a journal accepts. b. If the response to several query letters is negative, it is best to abandon attempts to get the information into print. c. Various journals use different formatting. Waiting until editor interest is expressed saves unneeded re-formatting. d. Some journals limit the number of items in the reference list. Best know this before editing the thesis down to the length of an article. e. Every contact with an editor results in at least a request for revisions. An initial manuscript cannot be prepared without editor input. ANS: A, C, D

Developing a manuscript for publication includes the following steps: (1) selecting a journal, (2) developing a query letter, (3) preparing a manuscript, (4) submitting the manuscript for review, and (5) revising the manuscript. A query is a letter an author sends to an editor, to ask the editor’s interest in reviewing a manuscript. This letter should be no more than one page in length and usually includes the abstract and the researcher’s qualifications for writing the article. If the response to the query letter is positive, then a manuscript should be prepared, according to the formatting and specifications of that publication. A negative response to a query letter merely implies that the journal is not interested in the topic of the submitted abstract. DIF: Cognitive Level: Comprehension 9. What should an abstract for quantitative research contain? (Select all that apply.) a. A table showing the demographic breakdown of the sample b. The name of the research method used c. A brief statement of the problem d. The research purpose e. The population or sample f. Operationalized variables g. The major study findings h. Conclusions ANS: B, C, D, E, G, H

Most research reports include an abstract that summarizes the key aspects of the study. The abstract of a study summarizes the key aspects of the study in 100 and 300 words and is the first component of a research report. Structured abstracts have specific headings such as problem, purpose, framework, methods, sample size, key results, and conclusions.

DIF: Cognitive Level: Application 10. What are the proper components of a query letter? (Select all that apply.) a. Suggestions for further research b. A description of the research problem c. The sample demographics d. Discussion of one or more of the major findings e. Academic or professional titles held by the letter writer f. Details of the study methodology g. The meaning of the study findings ANS: B, D, E, G

dissertation to a journal editor receives the following. “Dear Ms. Smith: “We have received your manuscript and are returning it to you. Our journal’s focus is exclusively quantitative research, and your manuscript uses a mixed methodology. Despite notable strengths of the quantitative portion, which contains cutting-edge information about medication errors and their correlates, our peer reviewers feel that you might be better served in seeking a venue that allowed both aspects of the study to be presented. The Nursing Journal of Mixed Methodologies springs to mind. “Nonetheless, if you should wish to resubmit only the quantitative portion, essentially as it stands, we should be quite interested in returning it to the peer reviewers. “Please see the one accompanying suggestion for table insertion.” What type of letter is it? (Select all that apply.) a. An outright rejection b. An acceptance c. An acceptance with minor revisions d. A rejection of the manuscript as currently written e. A suggestion for an alternative avenue of publication f. A compliment ANS: C, D, E, F

After reviewing a manuscript, the journal editor gathers the evaluations of all reviewers and reaches one of four possible decisions: (1) acceptance of the manuscript as submitted, (2) acceptance of the manuscript, pending minor revisions, (3) tentative acceptance of the manuscript pending major revisions, or (4) rejection of the manuscript. Acceptance of a manuscript as submitted is extremely rare. At the end of the revision process, the editor sends a letter that indicates acceptance and the likely date of publication. DIF: Cognitive Level: Analysis 12. What are the advantages of presenting a poster session, displayed for 2 hours a day for 3 days

at a well-attended conference, instead of a 15-minute verbal presentation with 5-minute question period, at a breakout session? (Select all that apply.)

a. For authors who suffer presentation anxiety, a poster presentation can be much less

stressful, since it provides many small conversations instead of a large lecture. b. A poster session allows the researcher to display more information than a verbal

presenter can. c. A poster presentation provides the opportunity for one-to-one interaction with the

viewers. d. The poster presentation may reach more people than does the verbal presentation. e. A verbal presentation requires more time to develop than does a poster. ANS: A, C, D

Research findings are communicated at conferences and meetings through verbal and poster presentations. Through podium presentations, researchers have an opportunity to share their findings with many persons at one time, answer a limited number of questions about their studies, interact formally with other interested professionals, and receive a small amount of immediate feedback on their study, concisely provided. The presentation developed depends on the audience and the time designated for each presentation. Time is probably the most important factor in developing a presentation because many presentations are limited to 10 or 15 minutes, with an additional 5 minutes for questions. As a guideline, one should aim for one slide per minute. A poster session is a collection of all the posters accepted at a conference in one central location. A poster is a visual presentation of a study, all on one surface. Poster sessions usually last 1 to 2 hours; the researcher should remain by the poster during this time and offer to answer any questions when a viewer is present. Through poster presentation, researchers have an opportunity to share their findings with a handful of persons at one time, answer unlimited questions, interact informally with other interested professionals, and receive thoughtful feedback, gently offered. Posters usually take 10 to 20 hours to develop, depending on the complexity of the study and the experience of the researcher. Novice researchers usually need more than 20 hours to develop a poster. One major advantage of a poster session is the opportunity for one-to-one interaction between the researcher and the viewer. At the end of the poster session, individuals interested in a study will frequently stay to speak to the researcher. A quality poster completely presents a study, yet can be comprehended in 5 minutes or less. DIF: Cognitive Level: Analysis 13. A journal states on its editorial page, “A query letter is required before article submission to

this refereed journal. If a manuscript is requested, both hard copy and an electronic copy will be required. After initial acknowledgement of receipt, authors will receive a response from the editor within 4 months.” What does this statement mean? (Select all that apply.) a. Within 4 months, the author will be notified whether the article is accepted. b. The author will be notified immediately of the manuscript’s acceptance. c. Only the editor reviews manuscripts. d. The journal uses peer review. e. If authors send a manuscript, without an initial query, it will be returned. f. If authors send a query letter, they will be requested to send a manuscript. g. If a manuscript is accepted, it will be published within 4 months. h. No manuscripts are ever accepted. ANS: A, D, E

A query letter is a letter an author sends to an editor, to ask the editor’s interest in reviewing a manuscript. This letter should be no more than one page in length and usually includes the abstract and the researcher’s qualifications for writing the article. Journals that require a query letter will not accept manuscripts without that initial query. A refereed journal is peer-reviewed and uses referees or expert reviewers to determine whether a manuscript is acceptable for publication. Most refereed journals require manuscripts to be reviewed anonymously, or blinded, by two or three reviewers. Most academic institutions support the refereed system and may recognize only publications that appear in peer-reviewed journals for faculty members seeking tenure and promotion. DIF: Cognitive Level: Comprehension 14. A master’s student has just completed a thesis. Which of the following are considered

dissemination of the results? (Select all that apply.) a. Interactions with the thesis committee—through reading the thesis, they have been informed of the results b. Presentation of a poster session at a professional conference c. Presentation of an oral (podium) presentation at a professional conference d. Presentation of a guest lecture about the thesis results at a university e. Having an article about the research results published by a journal f. Having an article about the research results published by a popular magazine ANS: B, C, D, E, F

Communicating research findings, the final step in the research process, involves developing a research report and disseminating the study findings through presentations and publications to audiences of nurses, healthcare professionals, policymakers, and healthcare consumers. DIF: Cognitive Level: Analysis

Chapter 28: Writing Research Proposals Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. Why do student research proposals usually require greater detail than those developed for

review by funding organizations? a. Student research proposals have a minimum page limit, because faculty members want their students to experience the worst-case scenario while in school, where support is readily available. b. Institutional review boards are very apprehensive about students performing research, and for this reason they require more detailed justification than do other proposals. c. Students do not write well, so their proposals tend to be more involved. d. Student proposals often contain the first three or four chapters of the student’s thesis or dissertation; funding proposals usually contain a much less detailed literature review. ANS: D

The content of a student proposal usually requires greater detail than a proposal developed for an agency or funding organization. The proposal is often the first three or four chapters of the student’s thesis or dissertation. The proposed study is discussed in the future tense—that is, what the student will do in conducting the research. A student research proposal usually includes a title page with the title of the proposal, the name and credentials of the investigator, university name, and the date. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. A formal, detailed research proposal is written. Which of the following would be reasons that

a researcher would write a detailed research proposal? (Select all that apply.) a. It is submitted before a nurse manager performs a quality improvement review of compliance with a new IV start protocol. b. It is required by a thesis or dissertation committee. c. It is submitted to gain institutional review board (IRB) approval. d. It is to be submitted for a funding grant. e. It is written to obtain support from one’s peers for a study conducted in a hospital medical-surgical unit. ANS: B, C, D

Researchers need to develop a quality study proposal to facilitate university and clinical agency IRB approval, obtain funding, and conduct the study successfully. Student researchers develop proposals to communicate their research projects to the faculty and members of university and agency IRBs. Student proposals are written to satisfy requirements for a degree and are usually developed according to guidelines outlined by the faculty. The content of a student proposal usually requires greater detail than a proposal developed for an agency or funding organization.

DIF: Cognitive Level: Application 2. What is the difference between a quantitative research proposal and a quantitative research

report? (Select all that apply.) a. The proposal precedes the study and is written to obtain permission or clearance for the research to be funded, take place, be approved at the research site, and so forth. b. They are identical. c. The research proposal does not contain results or discussion sections. d. The research report follows the study and includes both results of the study and a full discussion. e. The research report contains a framework, but the proposal does not. ANS: A, C, D

A research proposal is a written plan that identifies the major elements of a study, such as the research problem, purpose, literature review, and framework, and outlines the methods and procedures to conduct the proposed study. A proposal is a formal way to communicate ideas about a study to seek approval to conduct the study and obtain funding. Researchers who are seeking approval to conduct a study submit the proposal to a select group for review and, in many situations, verbally defend the proposal. Receiving approval to conduct research has become more complicated because of the increasing complexity of nursing studies, the difficulty involved in recruiting study participants, and increasing concerns over legal and ethical issues. A research report is the written description of a completed study designed to communicate study findings efficiently and effectively to nurses and other healthcare professionals. The information included in the report depends on the study, the intended audience, and the mechanisms chosen for dissemination. Usually research reports include four major sections or content areas: (1) introduction, (2) methods, (3) results, and (4) discussion of the findings. DIF: Cognitive Level: Synthesis 3. Which of the following elements do a research proposal and a research report have in

common? (Select all that apply.) a. Discussion b. Review of the literature c. Results d. Framework e. Methods f. Research problem g. Research purpose h. Introduction ANS: B, D, E, F, G, H

A research proposal is a written plan that identifies the major elements of a study, such as the research problem, purpose, literature review, and framework, and outlines the methods and procedures to conduct the proposed study. A proposal is a formal way to communicate ideas about a study to seek approval to conduct the study and obtain funding. Researchers who are seeking approval to conduct a study submit the proposal to a select group for review and, in many situations, verbally defend the proposal. Receiving approval to conduct research has become more complicated because of the increasing complexity of nursing studies, the difficulty involved in recruiting study participants, and increasing concerns over legal and ethical issues. Some journals limit the introduction to two or three brief paragraphs that include a statement about the theoretical framework for the study, a sufficient review of the literature to identify the gap in knowledge, and the clear purpose of the study. Other journals may require a background section that includes the significance of the study and a review of literature. DIF: Cognitive Level: Analysis 4. A researcher writes a preproposal. What exactly is a preproposal? (Select all that apply.) a. A justification for a research study b. A request for institutional review board approval c. A brief overview of a proposed project d. A first draft of a proposal e. A short document exploring funding opportunities for a research study ANS: C, E

Sometimes a researcher sends a preproposal or letter of intent rather than a proposal to a funding institution. A preproposal is a short document that explores the funding possibilities for a research project by businesses and corporations. The parts of the preproposal usually include: (1) the letter of transmittal, (2) brief proposal of a study, (3) personnel, (4) facilities, and (5) budget. The proposal provides a brief overview of the proposed project, including the research problem, purpose, methodology (brief description), and, most important, a statement of the significance of the work to knowledge in general and the funding institution in particular. By developing a letter of intent or a preproposal, researchers are able to determine the agencies interested in funding their study and limit submission of their proposals to only institutions that indicate an interest. DIF: Cognitive Level: Comprehension 5. When conducting a review of a proposal, which of the following questions would be

reasonable questions posed by an institutional review board (IRB)? (Select all that apply.) a. Is this study congruent with our hospital’s research agenda? b. What will be the impact of this study on our hospital and its clients? c. Is this proposal literate and well written? d. Does this study have any scientific merit? e. What prior research experience does this author have? f. Will the human subjects studied be protected from harm? g. What is the quality of this study? ANS: A, B, D, F, G

Clinical agencies and healthcare corporations review studies to evaluate the quality of the study and to ensure that adequate measures are being taken to protect human subjects. The administrators of an institution where the study is planned will also evaluate the impact of the study on the reviewing institution. IRB reviews sometime identify potential risks or problems related to studies that must be resolved before the studies are approved. In addition to scientific merit and human subjects’ protection, most agency IRBs evaluate proposals for the congruence of the study with the agency’s research agenda and the impact of the study on patient care. DIF: Cognitive Level: Comprehension 6. Why does a qualitative research proposal contain both the research philosophy and general

method and the applied method of inquiry? What is the distinction between these? (Select all that apply.) a. The research philosophy and general method are the name of the method—phenomenology, grounded theory, and so forth. b. The general method is the way the researcher plans to collect the data. c. The applied method of inquiry is the way the researcher plans to collect the data. d. The applied method refers to whether the study is phenomenology, grounded theory, ethnography, and so forth. e. They are both the same. ANS: A, B

Qualitative research proposals are unique because their methodology varies as the focus changes from understanding experiences, cultures, and times in history from the perspective of the persons in these situations. A qualitative proposal usually includes the following sections: (1) introduction and background, (2) review of the literature, (3) philosophical foundation for the selected method, and (4) method of inquiry. The philosophical foundation for the selected method section introduces the philosophical and conceptual foundation for the qualitative research method (phenomenological research, ethnographic research, grounded theory research, exploratory-descriptive qualitative research, or historical research) selected for the proposed study. Identifying the methods for conducting a qualitative study is a difficult task because sometimes the specifics of the study design emerge during the study. In contrast to quantitative research, in which the design is a fixed blueprint for a study, the design in qualitative research emerges or evolves as the study is conducted. The researcher must document the logic and appropriateness of the qualitative method and develop a tentative plan for conducting the study. Because this plan is tentative, researchers reserve the right to modify or change the plan as needed during the conduct of the study. However, the well-conceived design or plan will be consistent with the philosophical approach, study purpose, and specific research aims or questions. DIF: Cognitive Level: Analysis 7. Why should a qualitative research proposal intended for institutional board review address

methods, since methods can be flexible in qualitative research? (Select all that apply.) a. The committee must be aware of anything that will be done to the participants, including interviewing. b. The committee must adjudge potential harm that emanates from discussion of disturbing topics. c. The committee must be apprised of planned methods at the beginning of the study;

researchers must ask for permission if they decide add anything to the methods, while the study is in progress d. The forms for institutional review include this section, but it isn’t really addressed in qualitative research, since there is no intervention, per se. e. The committee must determine the relative risk of accidental disclosure of potentially embarrassing information. ANS: A, B, C, E

The sensitive nature of some qualitative studies increases the risk for participants, which makes ethical concerns and decisions a major focus of the study. Clinical agencies and healthcare corporations review studies to evaluate the quality of the study and to ensure that adequate measures are being taken to protect human subjects. Researchers hope to receive approval to collect data at the reviewing institution and to obtain support for the proposed study. IRB reviews sometime identify potential risks or problems related to studies that must be resolved before the studies are approved. DIF: Cognitive Level: Synthesis 8. Why might proposal revisions be required? (Select all that apply.) a. The review process may reveal unreasonable impact on one area of the institution,

since other research is in progress; a change of venue could be indicated. b. Funding becomes unavailable and the proposal must be revised, in accordance

with cuts. c. Several potential subjects refuse to participate in the research study. d. The study methodology is weak, and the reviewers’ suggestions will improve the

strength of the methodology. e. The researcher has inadvertently submitted materials that contain errors. ANS: A, B, D, E

Reviewers sometimes suggest changes in a proposal that improve the study methodology; however, some of the changes requested may benefit the institution but not the study. The researcher should remain receptive to the suggestions, explore with the committee the impact of the changes on the proposed study, and try to resolve any conflicts. Usually reviewers make valuable suggestions that might improve the quality of a study or facilitate the data collection process. Revision of the proposal is often based on these suggestions before the study is implemented. Sometimes a study requires revision while it is being conducted because of problems with data collection tools or subjects’ participation. However, if clinical agency personnel or representatives of funding institutions have approved a proposal, the researcher needs to consult with those who have approved and/or funded the study before making major changes in the study. Before revising a proposal, one should address three questions: (1) What needs to be changed? (2) Why is the change necessary? (3) How will the change affect implementation of the study and the study findings? DIF: Cognitive Level: Application

Chapter 29: Seeking Funding for Research Gray: Burns and Grove’s The Practice of Nursing Research, 9th Edition MULTIPLE CHOICE 1. What do the Association of Women’s Health, Obstetric, and Neonatal Nurses, National

Gerontological Nursing Association, and Emergency Nurses Association have in common, relative to funded research? a. All three were established, based on funded research. b. All provide proofreaders, free of charge, who will assist with grant writing. c. All three fund research. d. All three provide research guidance and funding through Sigma Theta Tau. ANS: C

Many nursing specialty organizations provide support for studies relevant to that specialty, including nurse practitioner groups. These organizations often provide guidance to new, less experienced researchers who need assistance in beginning the process of planning and seeking funding for research. To determine the resources provided by a particular nursing organization, search the organization’s website or contact the organization by e-mail, letter, or phone. Three of these nursing specialty organizations are the Association of Women’s Health, Obstetric, and Neonatal Nurses, National Gerontological Nursing Association, and Emergency Nurses Association. DIF: Cognitive Level: Analysis 2. A researcher receives a rejection letter concerning a proposal submitted for major funding.

What should the researcher do in a few weeks? a. The researcher should not apply for another grant for at least a year. b. The comments in the letter should be reviewed, so as to rewrite the proposal for the next review cycle. c. A formal protest should be filed. d. The contact person for the grant should be reached by e-mail as soon as possible. ANS: B

If a research grant proposal is unfunded, its author is not alone. In 2018, only 20.2% of all proposals submitted to NIH were funded (NIH, 2019c). The researcher’s reaction to a rejected proposal is usually anger and then depression. The frustrated researcher may want to abandon the proposal. There seems to be no way to avoid the subjective reaction to a rejection because of the significant emotion and time invested in writing the proposal. However, after a few weeks, it is advisable to examine the rejection letter and summary statement again. The comments can be useful in revising the proposal for resubmission. The learning experience of rewriting the proposal and evaluating the comments will provide a background for seeking funding for another study. Considering the low rate of acceptance, the researcher must be committed to submitting proposals repeatedly to achieve grant funding. DIF: Cognitive Level: Comprehension 3. What is the percentage rejection rate for new grant writers? a. Less than 20% b. Approximately 50%

c. 78% d. Greater than 78% ANS: D

If a research grant proposal is unfunded, its author is not alone. In 2018, only 20.2% of all proposals submitted to NIH were funded (NIH, 2019c). Considering the low rate of acceptance, the researcher must be committed to submitting proposals repeatedly to achieve grant funding. DIF: Cognitive Level: Analysis MULTIPLE RESPONSE 1. Why is seeking research funding important? (Select all that apply.) a. Funding implies both scientific and social merit. b. Funding allows the researcher to hire assistants who attend to the tasks of research, c. d. e. f.

leaving the researcher free for design of more and better projects. The academic reputation of the researcher increases as grant funding increases. Research cannot be conducted unless formal funding is obtained. Well-designed studies can be expensive, especially those with complex designs. A funded study is much more likely to be published.

ANS: A, B, C, E

Research funding is necessary for implementation of complex, well-designed studies. Simpler studies may be conducted with fewer resources, but even mailing a survey to an adequate-sized sample can be expensive. As the rigor and complexity of a study’s design increase, cost tends to increase proportionately. In addition to paying for expenses, funding also adds credibility to a study because it indicates that others have reviewed the study and recognize its scientific and social merit. The scientific credibility of the profession is related to the quality of studies conducted by its researchers. Thus, scientific credibility and funding for research are interrelated. The nursing profession has invested a great deal of energy in increasing the sources of funding and amount of money available for nursing research. Receiving funding enhances the professional status of the researcher and increases the possibilities of greater funding for later studies. Funding benefits the researcher because a grant may reimburse part or all of the researcher’s salary and release the researcher from other responsibilities, allowing the researcher to devote time to conducting the study. Funding may provide resources to hire research assistants and study coordinators to facilitate data collection and enhance the researcher’s productivity. DIF: Cognitive Level: Analysis 2. What are the advantages of a research apprenticeship? (Select all that apply.) a. Entree into a functional research team b. Extremely good wages c. Experience gained in grant writing d. A chance to read proposals that have been funded e. The opportunity to learn research and grantsmanship f. A chance to read proposals that have not been funded g. A guaranteed job after the apprenticeship ends ANS: A, C, D, E, F

Volunteering to assist with the activities of a seasoned researcher is an excellent way to learn research and grantsmanship. Graduate students can be paid and gain this experience by becoming graduate research assistants. Through directly working with an experienced funded researcher, one may gain experience in writing grants and reading proposals that have been funded. Examining proposals that have been rejected and the comments of the review committee can be useful, as well. The criticisms of the review committee point out the weaknesses of the study and clarify the reasons why the proposal was rejected. Examining these comments on the proposal can increase one’s insight as a new grant writer and prepare a novice for similar experiences. Some researchers are sensitive about these criticisms and may be reluctant to share them. If an experienced researcher is willing, however, it is enlightening to hear his or her perceptions and opinions about the criticisms. Ideally, by working closely with an experienced researcher, one has the opportunity to demonstrate one’s commitment, and the researcher may ultimately invite the novice to become a permanent member of a research team. DIF: Cognitive Level: Synthesis 3. Why is serving on a research committee or institutional review board useful for the person

interested in gaining research funding? (Select all that apply.) a. People who serve on research committees are given priority funding approval. b. Seeing the mistakes others make creates an awareness of common errors. c. Contacts with researchers can be made while serving in this capacity. d. When one’s own proposals are reviewed, the committee will feel more inclined to approve them. e. Reading a clear, organized proposal provides a template for future submission. ANS: B, C, E

Research committees and institutional review boards exist in many healthcare and professional organizations. Through membership on these committees, contacts with researchers can be made. Also, many research committees are involved in reviewing proposals for the funding of small grants or granting approval to collect data in an institution. Often reading proposals for approval for research involving human subjects or for funding can give the novice researcher insight into the importance of clarity and organization in the research proposal. Reviewing proposals and making decisions about funding are experiences that may help researchers become better able to critique and revise their own proposals before submitting them for review. DIF: Cognitive Level: Synthesis 4. What is the difference between a nursing project grant proposal and a nursing research grant?

(Select all that apply.) a. A research grant is awarded for a promising planned study. b. Research grants and project grants are identical. c. A project grant’s program can be academic or clinical. d. A research grant is awarded for outstanding past research. e. A project grant is awarded to support a novel program. ANS: A, C, E

Two main types of grants are sought in nursing: project grants and research grants. Project grant proposals are written to obtain funding for the development of new educational programs in nursing, such as a program designed to teach nurses to provide a new type of nursing care or as a project to support nursing students seeking advanced degrees. These grants may fund a project manager to achieve the goals of the grant. Although these programs may involve evaluation, they seldom involve research. For example, the effectiveness of a new approach to patient care may be evaluated, but the findings can seldom be generalized beyond the unit or institution in which the patient care was provided. The emphasis is on implementing the project, not on conducting research. Research grants provide funding to conduct a study. Although the two types of grant proposals have similarities, they have important differences in writing techniques, flow of ideas, and content. DIF: Cognitive Level: Synthesis 5. Many hospitals and universities have access to the Sponsored Programs Information Network

(SPIN). Why is this useful for a researcher? (Select all that apply.) a. They provide leads for thousands of grant opportunities. b. They provide information only for small grants of less than $5000 each. c. They provide information on federal agencies, private foundations, and corporate foundations. d. They are computerized information resources. e. They provide funding information; all fees are then used to support future grants. ANS: A, C, D

If one works in a hospital or university, the development department or other department responsible for fundraising for the institution can be very helpful because they have access to information about foundations. They likely have access to a computerized information system, the SPIN. This system allows searchers for information on specific foundations or on specific health conditions that are funded. One can then locate the most appropriate funding sources to support one’s research interests. The database contains approximately 2000 programs that provide information on federal agencies, private foundations, and corporate foundations. DIF: Cognitive Level: Analysis 6. A new researcher obtains a large grant and proceeds to hire nine assistants, as the grant

specifies. The new researcher hires a statistician, three persons to collect data, one person to schedule and coordinate the activities of the persons collecting data, one person to help with qualitative data analysis, one person to begin writing for the grant renewal, one person to write the interim report, and one person to manage the grant budget, writing weekly checks to the research assistants based on their submitted time cards. Which of these activities is appropriate for a hired assistant? (Select all that apply.) a. Advising the research team about appropriate statistical tests b. Recalculating the study power after data collection on the first thirty subjects, to be sure of the effect size c. Performing initial qualitative coding of raw data d. Writing the first draft of a renewal grant e. Writing the interim report for the institutional review board f. Managing the grant budget g. Writing weekly checks to the research assistants ANS: A, B, C, G

Although the supporting institution is ultimately responsible for dispensing and controlling grant monies, the primary investigator (PI) is responsible for monitoring budget expenditures and making decisions about how the money is to be spent. If funding is through a federal agency, the PI will be required to provide interim reports, as well as updates on the progress of the study. The PI interviews, hires, trains, and oversees grant personnel. During a large study with several investigators and other grant personnel, the PI coordinates activities, often through formal meetings of all grant workers at intervals to share ideas and solve problems. Federal grants require the submission of interim reports according to preset deadlines. The researcher should not wait until funding from the first grant has ended to begin seeking funding for a second study because of the length of time required to obtain funding. It may be wise to have several ongoing studies in various stages of implementation. For example, the PI could be planning one study, collecting data on a second study, analyzing data on a third study, and writing papers for publication on a fourth study. A full-time researcher could have completed one funded study, be in the last year of funding for a second study, be in the first year of funding for a third study, and be seeking funding for a fourth study. DIF: Cognitive Level: Application 7. What are two national nursing organizations that provide small grants not linked to a nursing

specialty area? (Select all that apply.) a. The Society for Pediatric Nurses b. American Nurses Foundation c. The Board of Registered Nursing d. The American Cancer Society e. Sigma Theta Tau International f. The National Association of Hospitals and Clinics ANS: B, E

Two national nursing organizations that provide small grants not linked to a specialty are the American Nurses Foundation and Sigma Theta Tau International. These grants are usually for less than $7500 each year, are very competitive, and are awarded to new investigators with promising ideas. Receiving funding from these organizations is held in high regard. DIF: Cognitive Level: Analysis