The aim of this project is to study some regression models used in Credit Scoring, in particular, the model which considers the incorporation of the default instant. It is natural that information are lost in this situation. One adequate form of studying the data of this nature is the construction of survival analysis models. The main objective of this work is to study the censuring effect in the estimation of the parameters in some Credit Score models adjusted by survival analysis. In this work, the right censure will be considered, and the study will be done using the Bootstrap simulation through the software SAS or R.
News published in Agência FAPESP Newsletter about the scholarship: