The Analytics of Risk Model Validation
A collection of papers in this new and developing area of research, this book focuses on the quantitative side of model validation and covers model validation in credit, market, and operational risk.
TABLE OF CONTENTS The Analytics of Risk Model Validation
7. Conclusions
7. Conclusions
With regard to measuring discriminatory power, the AR and the Area under the Curve seem promising [6.] tools as their statistical properties are well investigated and they are available together with many auxiliary features in most of the more popular statistical software packages.
With regard to testing calibration, for conditional PD estimates powerful tests such as the binomial, the Hosmer Lemeshow and the Spiegelhalter test are available. However, their appropriateness strongly depends on an independence assumption that needs to be justified on a case-by-case basis. Such independence assumptions can at least partly be avoided, but at the price of losing power as illustrated with a test procedure based on a normal approximation.
[6.] The selection of the topics and the point of view taken in this chapter is primarily a regulatory one. This is caused by the author s background in a regulatory authority. However, the presentation does not reflect any official regulatory thinking. The regulatory bias should be kept in mind when the following conclusions are read. A procedure that may be valuable for regulatory purposes need not necessarily also be appropriate for bank-internal applications.
Copyright Elsevier Ltd. 2008 under license agreement with Books24x7
