Assessing the default risk by means of a discrete-time survival analysis approach

Abstract

In this paper, the problem of company distress is assessed by means of a multi-period model that exploits the potentialities of the survival analysis approach when both survival times and regressors are measured at discrete points in time. The discrete-time hazards model can be used both as an empirical framework in the analysis of the causes of the deterioration process that leads to the default and as a tool for the prediction of the same event. Our results show that the prediction accuracy of the duration model is better than that provided by a single-period logistic model. It is also shown that the predictive power of the discrete-time survival analysis is enhanced when it is extended to allow for unobserved individual heterogeneity (frailty). Copyright © 2008 John Wiley & Sons, Ltd.