Van Keilegom, IngridWillems, StéphanieStéphanieWillems2025-05-142025-05-142025-05-142021https://hdl.handle.net/2078.2/24344Quantile regression is a statistical tool that has become increasingly popular over the last two decades. The idea behind this method is to evaluate how the quantiles of the distribution of the response variable vary with the explanatory variables. In this thesis, quantile regression will be used to study real unemployment data provided by the VDAB. As it often happens when analysing time-to-event data, a fraction of the individuals will never experience the event of interest. In the case of unemployment data, some individuals will indeed never find a job after a period of unemployment and will be considered as cured. In this context, classical quantile regression cannot be used as easily and new models had to be developed to take into account this cure fraction. The cure rate quantile regression developed by Han, Van Keilegom & Wang will be presented in this thesis and used to study the impact of different variables on the duration of unemployment. This new estimation method will allow to obtain estimators for the cure probability and for the quantile regression parameters.Quantile regressionCure modelstext::thesis::master thesisthesis:33205