Modeling Late Graduations: A Hidden Markov Model Approach

In this paper, we propose a hidden Markov model to investigate late graduation and dropout outcomes for university students by accounting for latent activity and inactivity periods in their careers. Data are based on the whole cohort of University La Sapienza students at the faculty of Economics enrolled in the academic year 2017/18. Model estimation is performed via a Bayesian approach. A Gibbs sampler algorithm is used to produce posterior estimates. Posterior smoothing probabilities provide an interpretable risk score that can support targeted institutional interventions.