Confidence Sets for Continuous-Time Rating Transition Probabilities

43 Pages Posted: 23 Jun 2004

See all articles by Jens Henrik Eggert Christensen

Jens Henrik Eggert Christensen

FRB of San Francisco - Financial Research

David Lando

Copenhagen Business School

Ernst Hansen

University of Copenhagen - Department of Applied Mathematics and Statistics

Date Written: March 15, 2004

Abstract

This paper addresses the estimation of default probabilities and associated confidence sets with special focus on rare events. Research on rating transition data has documented a tendency for recently downgraded issuers to be at an increased risk of experiencing further downgrades compared to issuers that have held the same rating for a longer period of time. To capture this non-Markov effect we introduce a continuous-time hidden Markov chain model in which downgraded firms enter into a hidden, 'excited' state. Using data from Moody's we show how to estimate the model, and conclude that both default probabilities and confidence sets are strongly influenced by the introduction of hidden, excited states.

Suggested Citation

Christensen, Jens Henrik Eggert and Lando, David and Hansen, Ernst, Confidence Sets for Continuous-Time Rating Transition Probabilities (March 15, 2004). EFA 2004 Maastricht Meetings Paper No. 4736. Available at SSRN: https://ssrn.com/abstract=556215 or http://dx.doi.org/10.2139/ssrn.556215

Jens Henrik Eggert Christensen

FRB of San Francisco - Financial Research ( email )

101 Market Street
San Francisco, CA 94105
United States
415-974-3115 (Phone)

David Lando (Contact Author)

Copenhagen Business School ( email )

Solbjerg Plads 3
Frederiksberg C, DK - 2000
Denmark
+45 3815 3600 (Fax)

Ernst Hansen

University of Copenhagen - Department of Applied Mathematics and Statistics

Universitetsparken 5
Copenhagen, DK-2100
Denmark

Register to save articles to
your library

Register

Paper statistics

Downloads
512
Abstract Views
2,952
rank
52,983
PlumX Metrics