Ankara University, Faculty of Educational Sciences, TURKEY.
Purpose: Studies in the literature have generally demonstrated that the causes of differential item functioning (DIF) are complex and not directly related to defined groups. The purpose of this study is to determine the DIF according to the mixture item response theory (MixIRT) model, based on the latent group approach, as well as the Mantel-Haenszel method, based on the observed group approach, compare the results, and determine the possible causes of the DIF.
Research Methods: As this study is contributing to the production of information to develop the theory, it is considered basic research. In accordance with the purposive sampling method, the research sample consisted of 1166 fourth-grade level students from Singapore, Kuwait, and Turkey who participated in the Trends in International Mathematics and Science Study mathematics application and took the sixth booklet. During the data analysis, the model that adapted the data according to MixIRT was determined. Then, the status of the items displaying DIF was determined according to the adaptive model.
Findings: According to the MixIRT, the two latent class models fit best to the data. No significant difference by gender was observed in either class or any country. This finding suggests that the gender variable, which is frequently used as the observed group in DIF studies, should not be dealt with alone.
Implications for Research and Practice: Since it is difficult to state whether an item is advantageous for a subgroup when DIF is determined in accordance with known groups, it is recommended to employ the latent class approach to determine DIF.
Keywords: Differential item functioning (DIF), causes of DIF, mixture item response theory, Mantel-Haenszel.