School absenteeism and Dropout - A Baysian duration model ∗

School absenteeism (or truancy) may be a signal of an ongoing process of student attrition that eventually leads to early school leaving. This paper estimates by a duration model the influence of school absenteeism on the risk of dropout in secondary education. In particular, using a semiparametric Cox duration model, the timing of the dropout decision of truants is compared with the timing of regular school attendees. Using administrative data with insights on wrongly specificied truancy spells, we correct in a Baysian duration model for issues on data uncertainty. We show that only a Baysian structure on the data yields insightful and consistent results. The analyis provides evidence of poor data validity on post-compulsory secondary school students aged 18 years old or older. Moreover, the results indicate that school-aged students enrolled in vocational education are most vulnarable to unauthorized school absenteeism and dropout. A relative risk ratio of 1.374 significant at 1%-level is estimated, indicating that truants are 37.4 percent more likely to dropout of school than regular school attendees.