Abstract
DIF detection using Logistic Discriminant Analysis and Polytomous Logistic Regression. This study focused on the effectiveness in polytomous item DIF detection using Logistic Discriminant Analysis and Polytomous Logistic Regression. The simulated test consisted of 30 items with five categories per item, where DIF was manipulated in six items of the test. The conditions under study were: DIF effect size (0.5, 1.0 and 1.5), sample size (500 and 1000) and DIF type (nonuniform). The results suggest that Logistic Discriminant Analysis is more accurate in DIF detection than Polytomous Logistic Regression. However, the false positives rates for both procedures were similar.