Comparison of WINSTEPS and difR to Detect DIF Using the Mantel-Haenszel Approach

• In Event: AERA Roundtable Session Sunday 11:40 am Four Seasons Ballroom 1
  In Roundtable Session: Advances in Differential Item Functioning (DIF) Detection: Methods, Applications, and Implications (Table 12)

Abstract

This study compares the performance of two software packages, WINSTEPS and difR, in detecting Differential Item Functioning (DIF) using the popular Mantel-Haenszel approach. The results from the analysis of real data indicate that the difR package generally identified fewer items as “C” items compared to WINSTEPS for the clinical tests, but more for the ability tests. The simulation study results suggest that while difR exhibits greater detection power compared to WINSTEPS, it also yields higher Type I error rates.

Authors

• Huan Liu, Riverside Insights

• Hyeonjoo J. Oh, Riverside Insights

• JongPil Kim, Riverside Insights