Paper Summary

Scale Comparability for Accommodated Forms in the Rasch Model: A Person-Fit Approach

Sat, April 14, 4:05 to 5:35pm, Marriott Pinnacle, Floor: Third Level, Pinnacle I

Abstract

The purpose of this study is to provide a valid approach and evidence of scale comparability for accommodated tests by using differential person functioning (DPF) as types of modeling-data misfit (person-fit). Although differential item functioning (DIF) is often investigated to rule out test unfairness as an explanation for the group difference, the unequal sample size and the size of samples have a significant effect on the statistical power of DIF detection procedure. One of the advantages of person-fit analysis is that even with a small sample sizes, it can be applied to investigate the scalability of examinees within different subgroups. This study demonstrates that person-fit analysis is appropriate for scale comparability study regardless of the size of the subgroups.

Authors