Differential Performance of Computerized Adaptive Testing in Students With and Without Disabilities – A Simulation Study

Abstract

Technologies that enable individualization for students have significant potential in special education. Computerized Adaptive Testing (CAT) refers to digital assessments that automatically adjust their difficulty level based on students' abilities, allowing for personalized, efficient, and accurate measurement. This article examines whether CAT performs differently for students with and without special educational needs (SEN). Two simulation studies were conducted using a sample of 709 third-grade students from general and special schools in Germany, who took a reading test. The results indicate that students with SEN were assessed with fewer items, reduced bias, and higher accuracy compared to students without SEN. However, measurement accuracy decreased, and test length increased for students whose abilities deviated more than two SD from the norm. We discuss potential adaptations of CAT for students with SEN in the classroom, as well as the integration of CAT with AI-supported feedback and tailored exercises within a digital learning environment.