Bankruptcy prediction using a discrete-time duration model incorporating temporal and macroeconomic dependencies

The purpose of this paper is to build an alternative method of bankruptcy prediction that accounts for some deficiencies in previous approaches that resulted in poor out‐of‐sample performances. Most of the traditional approaches suffer from restrictive presumptions and structural limitations and fai...

Full description

Saved in:
Bibliographic Details
Published in:Journal of forecasting 2008-09, Vol.27 (6), p.493-506
Main Authors: Nam, Chae Woo, Kim, Tong Suk, Park, Nam Jung, Lee, Hoe Kyung
Format: Article
Language:English
Subjects:
Bankruptcy
bankruptcy prediction
Correlation
Covariance
default correlation
discrete-time hazard model
duration-dependent hazard rate
Enterprises
Financial statements
Forecasting
Forecasts
Hazards
Macroeconomics
Modelling
Prediction
Property
Studies
Time
time-varying covariate
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The purpose of this paper is to build an alternative method of bankruptcy prediction that accounts for some deficiencies in previous approaches that resulted in poor out‐of‐sample performances. Most of the traditional approaches suffer from restrictive presumptions and structural limitations and fail to reflect the panel properties of financial statements and/or the common macroeconomic influence. Extending the work of Shumway (2001), we present a duration model with time‐varying covariates and a baseline hazard function incorporating macroeconomic dependencies. Using the proposed model, we investigate how the hazard rates of listed companies in the Korea Stock Exchange (KSE) are affected by changes in the macroeconomic environment and by time‐varying covariate vectors that show unique financial characteristics of each company. We also investigate out‐of‐sample forecasting performances of the suggested model and demonstrate improvements produced by allowing temporal and macroeconomic dependencies.  Copyright © 2008 John Wiley & Sons, Ltd.
ISSN:0277-6693
1099-131X
DOI:10.1002/for.985