DMCA
Multiperiod Corporate Default Prediction - A Forward Intensity Approach (2012)
Cached
Download Links
| Venue: | Journal of Econometrics |
| Citations: | 18 - 6 self |
BibTeX
@ARTICLE{Duan12multiperiodcorporate,
author = {Jin-chuan Duan and Andras Fulop},
title = {Multiperiod Corporate Default Prediction - A Forward Intensity Approach},
journal = {Journal of Econometrics},
year = {2012},
pages = {191--209}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The forward-intensity model of Duan, et al (2012) has proved to be a parsimonious and practical way for predicting corporate defaults over multiple horizons. However, it has a noticeable shortcoming because default correlations through intensities are conspicuously absent when the prediction horizon is more than one data period. We propose a new forward-intensity approach that builds in correlations among intensities of individual obligors by conditioning all forward intensities on the future values of some common variables, such as the observed interest rate and/or a latent frailty factor. Due to this conditioning, the new model no longer possesses the convenient decomposability property of the original forward-intensity model that can greatly simplify estimation and inference. For parameter estimation, we resort to a pseudo-Bayesian numerical device, and for statistical inference, we rely on the self-normalized asymptotics derived from recursive parameter estimates. The new model is implemented on a large sample of US industrial and financial firms spanning the period 1991-2011 on the monthly frequency. Our findings suggest that the new model is able to correct the structural biases at longer prediction horizons reported in Duan, et al (2012). Not surprisingly, default correlations are also found to be vital in describing the joint default behavior.
Keyphrases
new model default correlation prediction horizon corporate default financial firm parameter estimation noticeable shortcoming joint default behavior large sample original forward-intensity model new forward-intensity approach pseudo-bayesian numerical device data period future value recursive parameter estimate common variable self-normalized asymptotics forward intensity convenient decomposability property multiple horizon practical way latent frailty factor monthly frequency observed interest rate structural bias individual obligors forward-intensity model statistical inference
