Evaluating credit risk models : a critique and a proposal
- Evaluating the quality of credit portfolio risk models is an important issue for both banks and regulators. Lopez and Saidenberg (2000) suggest cross-sectional resampling techniques in order to make efficient use of available data. We show that their proposal disregards cross-sectional dependence in resampled portfolios, which renders standard statistical inference invalid. We proceed by suggesting the Berkowitz (1999) procedure, which relies on standard likelihood ratio tests performed on transformed default data. We simulate the power of this approach in various settings including one in which the test is extended to incorporate cross-sectional information. To compare the predictive ability of alternative models, we propose to use either Bonferroni bounds or the likelihood-ratio of the two models. Monte Carlo simulations show that a default history of ten years can be sufficient to resolve uncertainties currently present in credit risk modeling.
Verfasserangaben: | Hergen Frerichs, Gunter Löffler |
---|---|
URN: | urn:nbn:de:hebis:30:3-350418 |
URL: | http://ssrn.com/abstract=269575 |
DOI: | https://doi.org/10.2139/ssrn.269575 |
Dokumentart: | Konferenzveröffentlichung |
Sprache: | Englisch |
Jahr der Fertigstellung: | 2001 |
Jahr der Erstveröffentlichung: | 2001 |
Veröffentlichende Institution: | Universitätsbibliothek Johann Christian Senckenberg |
Datum der Freischaltung: | 17.09.2014 |
Freies Schlagwort / Tag: | backtesting,; bank regulation; credit risk; density forecasts; model validation |
GND-Schlagwort: | Kreditrisiko; Portfoliomanagement; Gütefunktion; Parametertest; Signifikanzniveau; Statistischer Test; Testtheorie |
Ausgabe / Heft: | Version: October 9, 2001 |
Seitenzahl: | 36 |
Bemerkung: | EFMA 2001 Lugano Meetings |
HeBIS-PPN: | 348154631 |
Institute: | Wirtschaftswissenschaften / Wirtschaftswissenschaften |
DDC-Klassifikation: | 3 Sozialwissenschaften / 33 Wirtschaft / 330 Wirtschaft |
JEL-Klassifikation: | C Mathematical and Quantitative Methods / C5 Econometric Modeling / C52 Model Evaluation and Selection |
Lizenz (Deutsch): | Deutsches Urheberrecht |