Poster #19 - Examining the Impact of Differential Item Functioning on Classification Accuracy in Cognitive Diagnostic Models

• In Event: 81.034 - MTCC Poster Session 20
  In Poster Session: 81.034-4 - Cognition and Assessment Poster Session

Abstract

Research in cognitive diagnostic models has increased over the past several years as demand for formative fine-grained assessment has grown. Theoretically, CDMs can provide this kind of feedback in a way that other models cannot. However, there has been limited research examining how known challenges to measurement impact CDM outcomes. While previous examinations of DIF in CDMs has focused on parameter recovery, none have examined the impact of DIF of CDM outcomes. In this paper, we provide initial findings examining this impact on classification accuracy at the level of individual attributes and attribute profiles. Initial findings suggest that CDMs are robust at the individual attribute level to DIF, while the attribute profiles are much less robust.

Authors

• Justin Paulsen, Indiana University - Bloomington

• Montserrat Beatriz Valdivia, Indiana University - Bloomington

• Dubravka Svetina Valdivia, Indiana University - Bloomington

• Yanan Feng, McKinsey & Company