Latent Variable Approach to Modelling Dependence of Credit Risks: Application to French Firms and Implications for Regulatory Capital

HEC Montreal Working Paper No. CREF 05-01

27 Pages Posted: 18 Jul 2005

See all articles by Sandra Foulcher

Sandra Foulcher

Banque de France

Christian Gourieroux

University of Toronto - Department of Economics; Center for Interuniversity Research and Analysis on Organization (CIRANO); Ecole Nationale de la Statistique et de l'Administration Economique (ENSAE); National Bureau of Economic Research (NBER)

André Tiomo

University Paris-Est Créteil (UPEC) - Institut de Recherche en Gestion

Date Written: March 2005

Abstract

This paper extends the analysis in Migration Correlation: Estimation Method and Application to the French Companies Rated by the Banque de France and provides a methodology for valuing dependent defaults based on the latent variable approach. This methodology underlies all models derived from the Merton's structural model and includes in particular the Basel II proposition. The latent correlation is calibrated by developing factor models that relate changes in unobservable variable to changes in a small number of economic factors. Our model exploits the relationship between the default correlation and the latent correlation throughout the joint probability of default. Using a comprehensive rating database managed by the Banque de France, we employ this relationship to calibrate latent correlations and finally to compute credit risk charges at a portfolio level.

Keywords: Latent correlation, default correlaiton, rating, credit risk, factor models, new basel accord

JEL Classification: G21, G33, C13

Suggested Citation

Foulcher, Sandra and Gourieroux, Christian and Tiomo, André, Latent Variable Approach to Modelling Dependence of Credit Risks: Application to French Firms and Implications for Regulatory Capital (March 2005). HEC Montreal Working Paper No. CREF 05-01, Available at SSRN: https://ssrn.com/abstract=757344 or http://dx.doi.org/10.2139/ssrn.757344

Sandra Foulcher

Banque de France ( email )

Paris
France

Christian Gourieroux

University of Toronto - Department of Economics ( email )

150 St. George Street
Toronto, Ontario M5S 3G7
Canada
416-978-4349 (Phone)
416-978-6713 (Fax)

Center for Interuniversity Research and Analysis on Organization (CIRANO) ( email )

2020 rue University, 25th Floor
Montreal, Quebec H3C 3J7
Canada

Ecole Nationale de la Statistique et de l'Administration Economique (ENSAE) ( email )

15 Boulevard Gabriel Peri
92245 Malakoff Cedex
France
33.4117.7666 (Fax)

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

André Tiomo (Contact Author)

University Paris-Est Créteil (UPEC) - Institut de Recherche en Gestion ( email )

80 Avenue du General de Gaulle
Creteil, 94000
France

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
215
Abstract Views
1,290
Rank
226,581
PlumX Metrics