Abstract

http://ssrn.com/abstract=1934808
 
 

References (31)



 
 

Citations (1)



 


 



Default Probability Estimation in Small Samples - With an Application to Sovereign Bonds


Walter Orth


University of Cologne - Department of Statistics and Econometrics

September 28, 2011

Discussion Papers in Statistics and Econometrics, University of Cologne, No. 05/2011

Abstract:     
In small samples and especially in the case of small true default probabilities, standard approaches to credit default probability estimation have certain drawbacks. Most importantly, standard estimators tend to underestimate the true default probability which is of course an undesirable property from the perspective of prudent risk management. As an alternative, we present an empirical Bayes approach to default probability estimation and apply the estimator to a comprehensive sample of Standard & Poor's rated sovereign bonds. We further investigate the properties of a standard estimator and the empirical Bayes estimator by means of a simulation study. We show that the empirical Bayes estimator is more conservative and more precise under realistic data generating processes.

Number of Pages in PDF File: 24

Keywords: Low-default portfolios, empirical Bayes, sovereign default risk, Basel II

JEL Classification: C11, C41, G15, G28

working papers series


Download This Paper

Date posted: September 28, 2011 ; Last revised: February 9, 2012

Suggested Citation

Orth, Walter, Default Probability Estimation in Small Samples - With an Application to Sovereign Bonds (September 28, 2011). Discussion Papers in Statistics and Econometrics, University of Cologne, No. 05/2011. Available at SSRN: http://ssrn.com/abstract=1934808 or http://dx.doi.org/10.2139/ssrn.1934808

Contact Information

Walter Orth (Contact Author)
University of Cologne - Department of Statistics and Econometrics ( email )
Albertus-Magnus-Platz
Cologne, DE 50923
Germany
(0049) 0221-470-6561 (Phone)
Feedback to SSRN


Paper statistics
Abstract Views: 474
Downloads: 99
Download Rank: 157,895
References:  31
Citations:  1

© 2014 Social Science Electronic Publishing, Inc. All Rights Reserved.  FAQ   Terms of Use   Privacy Policy   Copyright   Contact Us
This page was processed by apollo8 in 0.203 seconds