Gender differences in Italian STEM degree courses: a discrete-time competing-risks model

In this paper, we highlight possible gender differences in performance ofstudents attending Italian university STEM degree courses, controlling for sociodemographicand territorial variables.We used the micro-data from the Italian Ministryof Education, Universities and Research database of the 2011-12 freshmencohort enrolled at an Italian bachelor university degree course. The analysis wasdealt with by fitting a discrete-time competing-risks model. Bachelor degree graduation,dropout, and change to non-STEM courses were considered as competingevents. The aim is to highlight gender gaps in the student performance, and theSTEM courses where this gap is more critical.