An Odds Ratio Approach for Detecting DDF Under the Nested Logit Modeling Framework

Abstract

An odds ratio approach (ORA) under the framework of a nested logit model was proposed for evaluating differential distractor functioning (DDF) in multiple-choice items and was compared with an existing ORA developed under the nominal response model. The performances of the two ORAs for detecting DDF were investigated through an extensive simulation study. The impact of model misfit on the performance of each ORA was also examined. To facilitate practical interpretation of each method, effect size measures were obtained and compared. Finally, data from a college-level mathematics placement test were analyzed using the two approaches.