Facilitated by Dr. Jason Burns
Surveys can be a valuable means of gathering data 1) when the phenomena of interest are not directly observable, such as with satisfaction, professional commitment, and issues around culture and climate, and/or 2) when existing datasets do not contain the information needed to answer one’s research question(s). However, there are many ways that error, or inaccuracy, can be introduced during the process of conducting a survey. For instance, respondents may not understand an item, respondents may interpret the language used in an item in different ways, or the wording of items may steer respondents toward a particular answer. One way to reduce error in survey data is to employ a rigorous process when developing survey items - the set of questions that will be asked to respondents. This seminar provides an overview of the process of constructing high-quality survey items. Topics covered will include survey terminology, the characteristics that define high-quality survey items, common types of “poor” survey items, and how to evaluate items before using them in analysis.