Abstract: “The present study aims to perform a comparative analysis of 6 courses using the Rasch model with a sample of 1398 students (M = 12.5, SD = 0.67) from 8 schools in the province of Alicante (Spain). The fist data analysis showed a misfit of the model. After recoding the categories (from 9 to 4), a good fit was observed in most of the courses. The differential item functioning (DIF) by gender was significant in the visual arts education course. The measurement of a single latent construct is confirmed in this study.”

Keywords: educational evaluation, construct comparability approach, Rasch model