preview

Operational Definition.Pdf

Better Essays

Designing a Study Operational Definitions
The following chapter is excerpted from Designing HIV/AIDS Intervention Studies: An Operations Research Handbook, Andrew Fisher and James Foreit, 2002, Washington, DC: Population Council. (More on OR Handbook)

CHAPTER

6

OPERATIONAL DEFINITIONS
A fter formulating the study objectives and hypotheses and describing fully the study intervention, the next step in the research process is to define operationally the key variables and terms of the study. Operational definitions serve two essential purposes: (1) They establish the rules and procedures the research investigator will use to measure the key variables of the study, and (2) they provide unambiguous meaning to terms that otherwise might be …show more content…

According to the operational rules established, a person cannot be placed in the category “High Knowledge” and at the same time be placed in the “Medium,” “Low,” or “No” category. The categories are also totally inclusive. There are only four categories. There is no fifth, sixth, or seventh category that a respondent might fit into.

40

DESIGNING HIV/AIDS INTERVENTION STUDIES

In some instances, you may not want to be quite so specific in defining the categories of a variable before data collection. Sometimes it is preferable to determine the category “cutting points” of a variable after data have been collected and the response distribution for the variable has been examined. As a general rule, it is best to have approximately an equal number of respondents in each category. Thus, in the example above, each of the four categories of the variable—knowledge about HIV/AIDS transmission—should have approximately 25 percent of the respondents in the study population. If it is necessary to examine the response distribution of a variable before the procedures for establishing categories can be determined, then in the operational definition section of a study proposal the category names can be specified, but you should include a note indicating that each category will consist of approximately equal numbers of respondents. All variables must have at least two or more categories, or they are not

Get Access