ABSTRACT

This chapter explores the use of a particular version of the polytomous Rasch model to investigate measurement equivalence in comparative research settings. To understand the potential benefits of the mixed Rasch model for comparative analysis, it is necessary to understand the type of information that Rasch models provide on the individual items of a multiitem measurement instrument. The chapter demonstrates an application of the mixed Rasch model and discusses its interpretation. Beyond the general aspect of item response theory models being theoretically most appropriate for manifest indicators with ordinal response categories, the Rasch model has some features that make it attractive for comparative analyses from a methodological point of view. The software used for estimating the Rasch model is WinMira 1.45. In contrast, these models are widely used in educational attainment testing or physical ability evaluation in medical research.