Degree course change and student performance: a mixed-effect model approach

Abstract

This paper focuses on students credits earning speed over time and its determinants, dealing with the huge percentage of students who do not take the degree within the legal duration in the Italian University System. A new indicator for the performance of the student career is proposed on real data, concerning the cohort of students enrolled at a Faculty of the University of Palermo (followed for 7 years). The new indicator highlights a typical zero-inflated distribution and suggests to investigate the effect of the degree course (DC) change on the student career. A mixed-effect model for overdispersed data is considered, with the aim of taking into account the individual variability as well, due to the longitudinal nature of data. Results show the significant positive effect of the DC change on the student performance.

Keywords:

• university credits
• expected years to the graduation
• overdispersion
• ZIP model
• longitudinal data
• motion chart

Acknowledgements

The authors thank the Editors and the anonymous referees for their valuable comments which improved the quality and the clarity of the manuscript. The authors also gratefully acknowledge the support and useful comments of Vincenza Capursi, University of Palermo. The article is the result of the productive collaboration among the authors. In particular, Sections 1 and 4 can be ascribed to Giada Adelfio; Sections 2 and 3 to Giovanni Boscaino.

Disclosure statement

The dynamic version of the Bubble Chart illuatrated on Section 3 is available on http://www.unipa.it/gioboscaino/chart.html

Funding

This work was supported by University of Palermo, Italy [grant number 2012-ATE-0454], “Misure e modelli per la valutazione del Sistema Universitario”.