There are two familiar sayings in the research community. First, The first statement is a reflection of the normal state of the human condition, in which multiple factors usually influence a given phenomenon. Stated in research terms, at least several variables are related to the primary variable of interest. How, then, do you know which variables to study? For example, when conducting depression research with the elderly, some of the highly related variables that also should be included in a primary depression study might include physical health status, socialization, stress, coping, and access to resources. No one variable on its own can explain depression in this population. The second statementgarbage in, garbage outis common in the quantitative statistical community and is self-explanatory. If the quality of the measures and collected data are poor, every action and result that follows will also be poor, thus affecting reliability, validity, and credibility in a negative way. Optimally designed and executed survey studies prioritize measurement. They are reliable, meaning measurement is consistently applied. They are also valid, meaning truth and meaning in the measurement is applied. Finally, they are credible, meaning the results are subjectively, as well as objectively, believable. Refer back to the example in the Introduction for this week. Using a depression scale that consistently measures the specific construct of depression similarly with multiple measurement points and samples strengthens reliability. Using an instrument that measures the construct of depressionand not a similar construct such as grief, stress, or anxietystrengthens validity. Ensuring that your results relate to similar findings supported in the literature as well as within the community that works with depression in older adults also strengthens credibility.
