This study aims to explore psychometric characteristics and detect whether the teacher-made chemistry learning evaluation instrument contains item bias that can benefit students of a certain gender. The research sample was 358 students of class XII SMA in Yogyakarta who were taken by cluster random sampling then the answer were analyzed by Winsteps Rasch Software 3.73. In general, it can be concluded that the teacher-made chemistry learning achievement instrument is good in terms of the reliability coefficient, the distribution of the difficulty level of the items, the majority of which are in the medium category, and only one that detected as misfit item. The results of the analysis using the Mantel-Haenszel method showed that three item was biased and two of them favored male students. With the detection of bias item, it indicates that follow-up from the teacher is needed to improve these items so that the principle of test fairness can be enforced.
<p style="text-align: justify;">This study aimed to find the Classical Test Theory (CTT) and Modern Test Theory (MTT) item parameters of the Differential Aptitude Test (DAT) and examined their comparability of them. The item parameters being studied are difficulty level and discrimination index. 5.024 data of the result sub-test DAT were documented by the Department of Psychology and Guidance and Counselling bureau. The parameter of classical and modern test items was estimated and correlated by examining the comparability between parameters. The results show that there is a significant correlation between item parameter estimates. The Rasch and IRT 1-PL models have the highest correlation toward CTT regarding the item difficulty level. In contrast, model 2-PL has the highest correlation toward CTT in the item discrimination index. Overall, the study concluded that CTT and MTT were comparable in estimating item parameters of DAT and thus could be used independently or complementary in developing DAT.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.