A Latent Variable Approach to Validate Credit Rating Systems

14 Pages Posted: 19 Sep 2008

See all articles by Kurt Hornik

Kurt Hornik

Vienna University of Economics and Business Administration - Department of Statistics and Mathematics

Rainer Jankowitsch

WU (Vienna University of Economics and Business); Vienna Graduate School of Finance (VGSF)

Christoph Leitner

Vienna University of Economics and Business - Department of Statistics and Mathematics

Manuel Lingo

Oesterreichische Nationalbank (OeNB); Vienna University of Economics and Business Administration

Stefan Pichler

WU - Vienna University of Economics and Business - Department of Finance, Accounting and Statistics; VGSF (Vienna Graduate School of Finance)

Gerhard Winkler

Oesterreichische Nationalbank (OeNB); Vienna University of Economics and Business Administration

Date Written: September 17, 2008

Abstract

We suggest a new parametric framework to assess the accuracy of estimated default probabilities (PDs). Whereas the traditional methods to validate credit rating systems focus primarily on the discriminatory power, recent advances in credit risk management and banking regulation has shifted the focus of rating validation to the accuracy of PD estimates. In this paper we introduce bank and obligor specific error terms which are additive to a suitably transformed latent variable, which in our approach has the interpretation of the "true", unobservable PD of the underlying obligor. Provided with rating information from different sources (e.g., banks, rating tools, or rating agencies) and an appropriate model for the distribution of the latent PDs the parameters of the errors distribution can be obtained. In a specific application we assume the error terms to be jointly normal and estimate this model for a data set provided by the Austrian central bank where we observe PD estimates for 2090 obligors provided by 13 banks.

Keywords: Rating validation, latent variable, latent trait, probability of default

JEL Classification: G21, C33

Suggested Citation

Hornik, Kurt and Jankowitsch, Rainer and Leitner, Christoph and Lingo, Manuel and Pichler, Stefan and Winkler, Gerhard, A Latent Variable Approach to Validate Credit Rating Systems (September 17, 2008). Available at SSRN: https://ssrn.com/abstract=1269306 or http://dx.doi.org/10.2139/ssrn.1269306

Kurt Hornik

Vienna University of Economics and Business Administration - Department of Statistics and Mathematics ( email )

Vienna A-1090, Wien
Austria

Rainer Jankowitsch

WU (Vienna University of Economics and Business) ( email )

Welthandelsplatz 1
Vienna, Vienna AT1020
Austria
+43 1 31 336 4340 (Phone)
+43 1 310 0580 (Fax)

Vienna Graduate School of Finance (VGSF) ( email )

Welthandelsplatz 1
Vienna, 1020
Austria

Christoph Leitner

Vienna University of Economics and Business - Department of Statistics and Mathematics ( email )

Wien 1090
Austria

Manuel Lingo (Contact Author)

Oesterreichische Nationalbank (OeNB) ( email )

Otto-Wagner-Platz 3
1090 Vienna
Austria

Vienna University of Economics and Business Administration

Augasse 2-6
Vienna A-1090
Austria

Stefan Pichler

WU - Vienna University of Economics and Business - Department of Finance, Accounting and Statistics ( email )

Heiligenstaedter Strasse 46-48
Wien 1190
Austria

VGSF (Vienna Graduate School of Finance) ( email )

Heiligenstaedter Strasse 46-48
Vienna, 1190
Austria

Gerhard Winkler

Oesterreichische Nationalbank (OeNB) ( email )

Otto-Wagner-Platz 3
1090 Vienna
Austria

Vienna University of Economics and Business Administration ( email )

Welthandelsplatz 1
Vienna, Wien 1020
Austria

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
337
Abstract Views
2,185
rank
99,683
PlumX Metrics