Accommodations and Item-Level Analyses Using Mixture Differential Item Functioning Models

Abstract

The purpose of this study was to use differential item functioning (DIF) and latent mixture model analyses to explore factors that explain performance differences on a large-scale mathematics assessment between examinees allowed to use a calculator or who were afforded item presentation accommodations versus those who did not receive the same accommodations. Data from a state accountability assessment of mathematics for students in Grade 8 were analyzed. More than 73,000 students participated, of which 12,268 were students with disabilities (SWD) receiving test accommodations. DIF analyses detected performance differences between examinees without accommodations and those who used a calculator or those where the item presentation was altered. Latent performance class analyses revealed that performance differences were associated with item difficulty and abilty in addition to accommodation status. Results support validity studies that use mixture models that can consider context variables related to item type, academic skills, and accommodations.