SAMPLE SELECTION IN CREDIT-SCORING MODELS

We examine three models for sample selection that are relevant for mod eling credit scoring by commercial banks. A binary choice model is use d to examine the decision of whether or not to extend credit. The sele ctivity aspect enters because such models are based on samples of indi viduals to whom credit has already been given. A regression model with sample selection is suggested for predicting expenditures, or the amo unt of credit. The same considerations as in the binary choice case ap ply here. Finally, a model for counts of occurrences is described whic h could, in some settings also be treated as a model of sample selecti on. (C) 1998 Elsevier Science B.V.