IRT

Perhaps the degree of test difficulty is one of the most significant characteristics of a test. However, no empirical research on the difficulty of the MSRT test has been carried out. The current study attempts to fill the gap by utilizing a two-parameter item response model to investigate the psychometric properties (item difficulty and item discrimination) of the MSRT test. The Test Information Function (TIF) was also figured out to estimate how well the test at what range of ability distinguishes respondents. To this end, 328 graduate students (39.9% men and 60.1% women) were selected randomly from three universities in Isfahan. A version of MSRT English proficiency test was administered to the participants. The results supported the unidimensionality of the components of MSRT test. Analysis of difficulty and discrimination indices of the total test revealed that 14% of the test items were either easy / very easy, 38% were medium, and 48% were either difficult or very difficult. In addition, 14% of the total items were classified as nonfunctioning. They discriminated negatively or did not discriminate at all. 7% of the total items discriminated poorly, 17% discriminated moderately, and 62% discriminated either highly or perfectly, however they differentiated between high-ability and higher-ability test takers. Thus, 38% of the items displayed satisfactory difficulty. Too easy (14%) and too difficult (48%) items could be one potential reason why some items have low discriminating power. An auxiliary inspection of items by the MSRT test developers is indispensable.

This study is an investigation of gender equity in the context of the General English Achievement Test developed and used at Islamic Azad University (Isfahan Branch, IRAN), henceforth IAUGEAT, with test takers majoring in different fields of study. A sample of 835 students sitting for IAUGEAT was chosen purposively. The test scores were analyzed by the one-parameter IRT model. A focus group interview (10 test developers and language teachers) was also used to inquire into their perceptions about the impact of test takers’ gender and major on test equity. The findings of the DIF analysis indicated a reciprocal action between item type and gender DIF as some items exhibited DIF across different subgroups. In three subgroups, they favored female students. In one subgroup, they favored males. In the other two subgroups, they favored males and females alike. The qualitative data obtained from the focus group interview further confirmed the results. In general, our findings strongly suggest that checking gender equity via a Rasch-model DIF analysis is both eminent and convergent with a qualitative evaluation of test-takers' performance by test developers and instructors.