A Course in Item Response Theory and Modeling with Stata

Over the past several decades, item response theory (IRT) and item response modeling (IRM) have become increasingly popular in the behavioral, educational, social, business, marketing, clinical, and health sciences. In this book, Raykov and Marcoulides begin with a nontraditional approach to IRT and IRM that is based on their connections to classical test theory, (nonlinear) factor analysis, generalized linear modeling, and logistic regression. Application-oriented discussions follow next. These cover the one-, two-, and three-parameter logistic models, polytomous item response models (with nominal or ordinal items), item and test information functions, instrument construction and development, hybrid models, differential item functioning, and an introduction to multidimensional IRT and IRM. The pertinent analytic and modeling capabilities of Stata are thoroughly discussed, highlighted, and illustrated on empirical examples from behavioral and social research.

Notation and typography. What is item response theory and item response modeling? Two basic functions for item response theory and item response. Classical test theory, factor analysis, and their connections to item response theory Generalized linear modeling, logistic regression, nonlinear factor analysis, and their links to item response theory and item response modeling. Fundamentals of item response theory and item response modeling. First applications of Stata for item response modeling. Item response theory model fitting and estimation. Information functions and test characteristic curves Instrument construction and development using information functions. Differential item functioning. Polytomous item response models and hybrid models. Introduction to multidimensional item response theory and modeling

Tenko Raykov is Professor of Measurement and Quantitative Methods at Michigan State University. George A. Marcoulides is Distinguished Professor of Research Methodology in the Department of Education at The Gervitz Graduate School of Education and a member of the Quantitative Methodology in Social Sciences Program at the University of California, Santa Barbara.