Probability of deafault using the logit model: The impact of explanatory variable and data base selection

Abstract

The Spanish economy is suffering a severe financial crisis which is affecting all Spanish savings banks as well as some major banks. One of the triggers of the crisis is the high companies’ default rate experienced in the last years due to a deficient credit risk management by financial institutions. Credit risk analysis is mainly undertaken using the logit model to calculate the probability of default of the companies. In this work we describe some problems that arise when using this model and that can have a negative impact on the quality of the results obtained.