Estimating the number of changepoints in segmented regression models: comparative study and application

This paper deals with the problem of selecting the number of changepoints in segmented regression models. The aim is to review selection criteria, namely information criteria and hypothesis testing, and to propose a novel application in the context of students' careers in higher education. The performance of the selection criteria is assessed through simulation studies. Furthermore, we investigate the relationship between University students' performances and one of their main determinants, finding out that this relationship is actually broken-line.