Examining Group Differences in Mathematics Achievement: Explanatory Item Response Model Application
Abstract
Students take many different exams throughout their educational lives. In these exams, various individual and item characteristics can affect the responses of individuals to the items. In this study, it was aimed to examine the effects of person and item predictors on the mathematics common exam results of 365 9th grade students with explanatory item response models. Gender and school type as person variables and cognitive domain, content domain and booklet type as item variables were added to the models due to their widespread inclusion in the literature. When the predicted item parameters were examined, it was seen that the smallest parameter values were obtained for all items with the Rasch model. When the model data fit values of four different models were examined, it was concluded that the latent regression and latent regression linear logistic test models showed better fit than the Rasch model. By adding person and item predictors to the model, the parameters obtained for each variable group were compared, and differences were observed between the groups for school type, cognitive domain, and content domain variables. It was concluded that the item parameters did not differ for the variables of gender and booklet type. It is thought that it would be beneficial to use these models more widely in studies to be conducted in the field of education and psychology since they provide more detailed information about the reasons for the differences in the estimated parameters.
Keywords
Explanatory item response models , rasch model , math success
References
- Atar, B. (2011). Tanımlayıcı ve açıklayıcı madde tepki modellerinin TIMSS 2007 Türkiye matematik verisine uyarlanması. Eğitim ve Bilim, 36(159).
- Atar, B., & Aktan, D. Ç. (2013). Birey açıklayıcı madde tepki kuramı analizi: örtük regresyon iki parametreli lojistik modeli. Eğitim ve Bilim, 38(168).
- Baker, F. B. (2001). The basics of item response theory. http://ericae. net/irt/baker. Berberoğlu G. ve Kalender İ. (2005). Öğrenci Başarısının Yıllara, Okul Türlerine, Bölgelere Göre İncelenmesi: ÖSS ve PISA Analizi, ODTÜ Eğitim Bilimleri ve Uygulama Dergisi, Sayfa 27-28.
- Blozis, S. A., Conger K. J., & Harring, J. R. (2007). Nonlinear latent curve models for multivariate longitudinal data. International Journal of Behavioral Development: Special Issue on Longitudinal Modeling of Developmental Processes, 31, 340-346
- Boeck, P. de, Cho, S. J., & Wilson, M. (2011). Explanatory secondary dimension modeling of latent differential item functioning. Applied Psychological Measurement, 35(8), 583–603.
- Boeck, P. de., &Wilson, M. (2004). Explanatory item response models. New York, NY: Springer New York.
- Briggs, D. C. (2008). Using explanatory item response models to analyze group differences in science achievement. Applied Measurement in Education, 21(2), 89–118.
- Bulut, O. (2021). eirm: Explanatory item response modeling for dichotomous and polytomous item responses, R package version 0.4. doi: 10.5281/zenodo.4556285 Available from https://CRAN.R-project.org/package=eirm.
- Bulut, O., Palma, J., Rodriguez, M. C., & Stanke, L. (2015). Evaluating measurement invariance in the measurement of developmental assets in Latino English language groups across developmental stages. Sage Open, 5(2), 2158244015586238.
- Büyükkıdık, S., & Bulut, O. (2022). Analyzing the Effects of Test, Student, and School Predictors on Science Achievement: An Explanatory IRT Modeling Approach. Journal of Measurement and Evaluation in Education and Psychology, 13(1), 40-53.