摘要：Model-data fit indices for raters provide insight into the degree to which raters demonstrate psychometric properties defined as useful within a measurement framework. Fit statistics for raters are particularly relevant within frameworks based on invariant measurement, such as Rasch measurement theory and Mokken scale analysis. A simple approach to examining invariance is to examine assessment data for evidence of Guttman errors. I used real and simulated data to illustrate and explore a nonparametric procedure for evaluating rater errors based on Guttman errors and to examine the alignment between Guttman errors and other indices of rater fit. The results suggested that researchers and practitioners can use summaries of Guttman errors to identify raters who exhibit misfit. Furthermore, results from the comparisons between summaries of Guttman errors and parametric fit statistics suggested that both approaches detect similar problematic measurement characteristics. Specifically, raters who exhibit many Guttman errors tended to have higher-than-expected Outfit MSE statistics and lower-than-expected estimated slope statistics. I discuss implications of these results as they relate to research and practice for rater-mediated assessments.
