Categorical Data Analysis with a Psychometric Twist

Variables measured in psychological and social science research are often discrete, such as the choice between two objects in a paired comparison experiment, the response option selected on a survey item, the correct answer on a test question, career choice, gender, the highest degree earned, and many others. The focus of this chapter is on models for discrete data such as those often collected in psychological and educational research. The statistical models presented in this chapter fall within the class of generalized linear models (GLM). The GLM framework provides a unification of numerous models proposed in statistics, medicine, economics, sociology, and psychology.