Analysis of reporting behavior using generalized ordered probit models : an introduction to the hopit package

The ordered response data classify a measure of interest into ordered categories collected during a survey. For example, if the dependent variable is a happiness rating, then a respondent typically answers a question such as: “Taking all things together, would you say you are . . . ?”; and then selects from response options such as:”very happy“,”pretty happy“,”not too happy“, and”very unhappy" (Liao, Fu, and Yi 2005). Similarly, if interviewees are asked to evaluate their health in general (e.g., “Would you say your health is . . . ?”), they may choose among several categories, such as “very good”, “good”, “fair”, “bad”, and “very bad” (King et al. 2004; Jürges 2007; Rebelo and Pereira 2014; Oksuzyan et al. 2019). In political science, a respondent may be asked for an opinion about recent legislation (e.g. “Rate your feelings about the proposed legislation.”) and asked to choose among categories like “strongly oppose”, “mildly oppose”, “indifferent”, “mildly support”, and “strongly support” (Greene and Hensher 2010). It is easy to imagine other multi-level ordinal variables that might be used during a survey and to which the methodology described below could be applied.