VARIABLES

A variable is a characteristic or property that takes on different values in different persons, places or things. Variables are measurable by data. The variables determined may be for any study at any level, be it local, national, or international. In medical research, they assess changes in health or disease situations.

Variables generally fall in one of two categories:

1. Qualitative (discrete) variables.

2. Quantitative (continuous) variables.

3. Hybrid variable.

Qualitative (categorical) variables

Qualitative variables are variables where the magnitude or size of the characteristic or attribute as the same cannot be measured. They are classified by counting the number of people having or reporting the same characteristic or attribute, and not by measurement. In this case, there is only one variable: the number of people. Qualitative variables are discrete in nature, so they are sometimes referred to as discrete variables.

Qualitative variables are typically used in clinical trials, usually to collect information on the action of the drug or its efficacy. They are also used in surveys, as part of pilot studies.

Qualitative variables are particularly suited to gaining understanding of people‖s lived worlds, that is, how people experience and view, believe and think, aspire and assess the world about them. They may be used to generate hypotheses that can then be tested by other variables. Qualitative variables are also very vital in pilot studies and also may be used to collect data that help to interpret statistical material.

Examples of qualitative variables are blood groups, the presence of disease, and the type of drug used to treat a disease. Blood group is a qualitative variable because it cannot be measured. Rather, it is classified into four groups: A, B, AB, or O.

Qualitative variables can be further classified into:

1. Nominal.

2. Ordinal.

3. Binary.

1. Nominal variables

Nominal variables represent names or categories. Examples include blood type, gender, marital status, hair color, etiology, and presence versus absence of a risk factor or disease, and vital status. Nominal variables represent the weakest level of measurement as they have no intrinsic order or other mathematical properties and allow only for qualitative classification or grouping.

2. Ordinal variables

Ordinal variables are considered to be semiquantitative. They are similar to nominal variables in that they are composed of categories, but their categories are arranged in a meaningful sequence (rank order), such that successive values indicate more or less of some quantity (i.e., relative magnitude). Typical examples of ordinal variables include socioeconomic status, tumor classification scores, New York Heart Association (NYHA) functional class for angina or heart failure, disease severity, birth order, perceived level of pain, and all opinion survey scores.

3. Binary variables

Binary variables are variables that can take two possible values. Some examples of binary variables include male or female, true or false, yes and no, etc. There are two types of binary variables: opposite and conjunct. Opposite binary variables, most common, are binary variables whose two possible values are opposites like yes or no, and true and false. Conjunct binary variables are variables whose possible values aren‖t exactly opposite like political preference in the US. where you can prefer democrats or republicans.

Quantitative (numerical) variables

Quantitative variables are measurable variables. They possess a magnitude; they can be measured numerically. Quantitative variables are measured on an interval or on a ratio scale.

The quantitative data are also known as continuous data, since each individual has one measurement from a continuous spectrum or range such as body temperature from 35–42°C.

The characteristic may be measurable in whole numbers and fractions such as chest circumference: 33 cm, 34.5 cm, 35.2 cm, 36 cm, 37.3 cm and so on or it may be measurable or countable in discrete whole numbers only, such as pulse rate, cholesterol, blood pressure, ESR, blood sugar, etc.

Data in quantitative variables are collected by using laboratory tests or patient response questionnaires and surveys that ask the respondent how much or how many. Quantitative data may be displayed graphically or summarized and otherwise analyzed through the use of descriptive and/or inferential statistics.

Quantitative variables can be further classified into:

 Continuous.

 Discrete.

Continuous variables

Continuous variables are variables that can theoretically take on any value along a continuum. They are characterized by the measurement of ranges of variables. For example, “age” is a continuous variable because, theoretically at least, someone can be any age. “Income,” “weight,” and “height” are other examples of continuous variables.

Discrete variables (Counts)

Discrete variables (e.g., number of dental caries, number of white cells per cubic centimeter of blood, number of readers of medical journals, or other count-based data) can take on only whole numbers. Data acquired over time or space may be expressed in discrete numbers.

Scientific experiments have several types of variables. The independent and dependent variables are the ones usually plotted on a chart or graph, but there are other types of variables you may encounter.

Type Independent Variable Dependent Variable Controlled Variable

Definition The independent variable is the one condition that you change in an experiment.

The dependent variable is the variable that you measure or observe.

The dependent variable gets its name because it is the factor that is dependent on the state of the independent variable.

A controlled variable or constant variable is a variable that does not change during an experiment.

Example In an experiment measuring the effect of temperature on solubility, the independent variable is temperature.

In the experiment measuring the effect of temperature on solubility, solubility would be the dependent variable.

In the experiment measuring the effect of temperature on solubility, controlled variables could include the source of water used in the experiment, the size and type of containers used to mix chemicals, and the amount of mixing time allowed for each solution.

Additionally, Extraneous and Confounding Variables

Extraneous variables are all variables, which are not the independent variable, but could affect the results of the experiment. Extraneous variables that are not recognized until the study is in process or recognized but cannot be controlled are called confounding variables. Confounding variables can sometimes be measured, but in most cases, these variables cannot be measured and should then be included in the study limitations as they‖re bound to hinder the interpretation of the findings. (Burns & Grove, 2001).