An Evaluation of DIF Tests in Multistage Tests for Continuous Covariates

Multistage tests are a widely used and efficient type of test presentation that aims to provide accurate ability estimates while keeping the relatively short. typically rely on psychometric framework item response theory. Violations models other assumptions underlying multistage test, such as differential functioning, can lead inaccurate unfair measurements. There is practical need for methods detect problematic model violations avoid these issues. This study compares evaluates three detection functioning with regard continuous person covariates in data from tests: linear logistic regression two adaptations recently proposed score-based DIF test. While all show satisfactory Type I error rate, greater power against types effects.