Model Comparison in Item Response Theory Modeling
Ezgi Aytürk Ergin, Fordham University
Abstract: Item response theory (IRT) is a set of latent variable techniques for modeling responses to psychometric tools such as tests and questionnaires. Every IRT model has a set of assumptions regarding how item properties (e.g., difficulty, discrimination) and the latent variable of interest interact to determine item response. Consequently, IRT models vary in their model complexity, and the scoring of respondents on the latent trait depends on the specific IRT model chosen. In my talk I will present two studies: First, I will present a study where we (a) modified an existing depression scale for a more accurate evaluation of depression in cancer patients and (b) selected an IRT model that best represented the responses to this modified scale. In presenting this study, I will focus on the practice of using goodness-of-fit indices in IRT model comparison. Second, I will present my recent work showing that current IRT goodness-of-fit indices do not properly account for the differences in the complexities of IRT models and that they systematically favor more complex models regardless of the data. I will discuss the implications of the findings and future directions in this line of research.
MAY 7, 2021 Friday
Meeting ID: 997 3229 3808