Evidence-Based LP by Read Hayes, Ph.D., CPP Dr. Hayes is director of the Loss Prevention Research Council and coordinator of the Loss Prevention Research Team at the University of Florida. He can be reached at 321-303-6193 or via email at rhayes@lpresearch.org. © 2011 Loss Prevention Research Council
Research Fundamentals T
There can also be two types of data—qualitative and quantitative. We usually call data quantitative if it is in numerical
his column is dedicated to supporting all LP professionals. Hopefully sharing research findings, crime-prevention concepts, and research methods helps all of us get better at getting adequate budgets, as well as understanding and preventing crime. In the last column we discussed how LP experts can use situational crime-prevention concepts or theory to design and improve crime and loss control impact. This column is more about how research works and how to use it to get better.
form and qualitative if not. Photographs, videos, and sound recordings can be considered qualitative data. A very important research concept is the unit of analysis. The unit of analysis is key since we want to explain variance between members of the unit of analysis in a study such as: ■ I ndividuals (employees, offenders), ■ P laces (stores, DCs), ■ G roups (managers, customers, districts), and ■ I nteractions (crime-prevention treatments, loss levels, sales levels).
The Language of Research
Research is a lot like any topic, you should know the science jargon. We then take on some of the major issues in research like what questions are we trying to answer, and what’s the best way to answer key questions. So, we turn to some important terms like variable, hypothesis, data, and unit of analysis. Two terms, theoretical and empirical, actually work together with theoretical meaning developing, exploring, or testing how something really operates. Empirical means actual observed and measured perceptions of that something. Most research blends these two terms by comparing how our theories about how the world operates with our actual observations of its operation. Most crime prevention research is probabilistic, or based on probabilities. The inferences we make in research have probabilities associated with them, which is why statistics are so important in our research since they allow us to estimate probabilities for the situations we study. Another critical term is causal, meaning much of our research describes relationships or opinions, but most of our randomized controlled trials and cross-sectional predictive analytics explore relationships between a certain theft-reduction countermeasure and the observed loss level. Most of us have heard there can be a difference between a correlational relationship and a causal relationship. With so much at stake in LP like serious injuries, loss of reputation, and heavy financial losses, most research should help identify crime and loss causes. We can’t do a lot of research unless we discuss variables. A variable is any entity that can take on different values. A hypothesis is a specific statement of prediction or relationship. It describes what we expect will happen in our study. Not all studies have hypotheses. Sometimes a study is designed to be exploratory in order to later develop hypotheses.
66
May – June 2011
Deductive and Inductive Thinking
In logic we often refer to the two broad methods of reasoning as the deductive and inductive approaches. Deductive reasoning works from the more general to the more specific. Sometimes this is informally called a “top-down” approach. We might begin with thinking up a theory about our topic of interest. We then narrow that down into more specific hypotheses that we can test. We narrow down even further when we collect observations to address the hypotheses. This ultimately leads us to be able to test the hypotheses with specific data—a confirmation (or not) of our original theories. Inductive reasoning works the other way, moving from specific observations to broader generalizations and theories. Informally, we sometimes call this a “bottom-up” approach. In inductive reasoning, we begin with specific observations and measures, begin to detect patterns and regularities, formulate some tentative hypotheses that we can explore, and finally end up developing some general conclusions or theories.
Making a Difference
As mentioned last issue, you should carefully diagnose your specific problem and then adjust the proposed solutions. Your research should include hypothesizing about what, who, when, where, why, how much, and how the problem is occurring. Then collect incident, interview, survey, and experimental data to support, adjust, or not support what you thought. Good research should help your team much better understand loss dynamics, how well or not crime-prevention treatments work, and provide clear descriptions for senior executives as they decide whether to fund your LP programs.
|
LPportal.com
