The performance of DIF-free-then-DIF strategy in MIMIC method

Chu-Chu TSAI, Wen Chung WANG, Ching Lin SHIH

Research output: Contribution to conferencePaper

Abstract

To control Type I error rates in assessing differential item functioning, constant item (CI) method was proposed in literature. The performance of CI method was found highly correlated to the anchor items. The strategy to select several items as anchor first and then assessing DIF for other items in the test was called DIF-free-then-DIF strategy (DFTD; Wang, 2008). It was found the more DIF-free items in the anchor test, the better performance of DFTD strategy. However, in Wang and Shih (2010), the anchor items were DIF-free by design. To implement the DFTD strategy into practice, the anchor should be selected and the performance of DFTD strategy can be better assessed with the selected anchor. In this study, the performance of DFTD strategy was assessed in the MIMIC method through simulation study. Four independent variables were included in this study: sample size, percentage of DIF items in the test, DIF assessment method, and anchor item selection method. Our findings and conclusions will be given in details in the presentation.
Original languageEnglish
Publication statusPublished - Jul 2011

Fingerprint

Anchors

Citation

Tsai, C.-C., Wang, W. C., & Shih, C.-L. (2011, July). The performance of DIF-free-then-DIF strategy in MIMIC method. Paper presented at the 76th Annual and the 17th International Meeting of the Psychometric Society, The Hong Kong Institute of Education, China.