A Comprehensive Simulation Study of Estimation Methods for the Rasch Model

The Rasch model is one of the most prominent item response models. In this article, different parameter estimation methods for are systematically compared through a comprehensive simulation study: Different alternatives joint maximum likelihood (JML) estimation, marginal (MML) conditional (CML) and several limited information (LIM). type ability distribution (i.e., nonnormality), number items, sample size, difficulties were varied. Across conditions, MML with flexible distributional specifications can be at least as efficient CML. Moreover, in many situations long tests), penalized JML ε adjustment resulted very estimates might considered to implementations currently used statistical software. minimum chi-square (MINCHI) was best-performing LIM method. These findings demonstrate that still prove helpful applied research.