Analysis of the career length of professional basketball players by means of survival analysis

Details

Supervisors

Van Keilegom, Ingrid

Faculty

Faculté des sciences

Degree label

Master [120] en science des données, orientation statistique, à finalité spécialisée

Abstract

enThe goal of this thesis is to apply survival analysis to the specific case of professional basketball career length. To do so, we use two different datasets and apply multiple survival analysis techniques on them: Kaplan-Meier, Cox regression, Random Survival Forests and Survival Support Vector Machine. These techniques allow us to explore the associations between career length of NBA players and a set of covariates, and to assess predictive performance. We end this thesis by discussing the limitations and the opportunities for future studies.