Item response theory to discriminate COVID-19 knowledge and attitudes among university students

Abstract

The study sought to compare two-item response theory (IRT) models, the Rasch and 2PL models, and to uncover insights on COVID-19 knowledge and attitude item difficulty and discrimination among university students. We premise this study on ITM to argue that logical flow, degree of difficulty, and discrimination of items for the constructs among respondents contribute to the validity and quality of statistical inferences. The developed Rasch and 2PL models are compared to determine the difficulty and discrimination of knowledge and attitude items, with an application to COVID-19. Our results show that although the Rasch and 2PL models provide rich diagnostic tools to understand multiple traits, the 2PL model provides more robust results for the assessment of knowledge and attitude of students about the COVID-19 epidemic. Moreover, of the two constructs, the items for the attitude construct recieved more reliable responses than the knowledge construct items. Accordingly, under any pandemic, the lack of proper and evolving knowledge could have dire consequences; hence, strict efforts should be made while designing knowledge items.