Estimation of Default Probabilities Using Incomplete Contracts Data
This paper develops a count data model for credit scoring which allows the estimation of default probabilities using incomplete contracts data. The model is based on the beta-binomial distribution, which is found to be particularly adequate to describe this sort of data. A well known data set on personal loans granted by a Spanish bank is used to illustrate the application of the proposed model.
JEL Classification: C21, C51, G21.
Keywords: Beta-binomial distribution; Credit scoring; Hurdle models.