Croon-Based Estimation for Small Sample Explanatory Item Response Models

• In Event: Advances in Item Response Theory Modeling and Application

Abstract

Explanatory item response modeling (EIRM) and structural equation modeling (SEM) with maximum likelihood (ML) estimation are the predominant methods to empirically assess complex theories involving multiple latent variables captured through categorical indicators. Although ML methods have many desirable properties including consistency, a major limitation in complex models with categorical indicators is that they often sustain significant bias when implemented in small to moderate size studies. Recent literature has developed a method of moments corrected maximum likelihood limited information estimator designed to address this limitation that has been shown to produce unbiased and efficient estimates in small to moderate sample settings. In this study, we extend Croon’s bias-corrected estimator to models that draw on categorical indicators (e.g., item response theory).

Authors

• Benjamin Kelcey, University of Cincinnati

• Fangxing Bai, University of Cincinnati

• Yanli Xie, University of Cincinnati