The Basel II Risk Parameters pp 1-12 | Cite as
Statistical Methods to Develop Rating Models
Abstract
The Internal Rating Based Approach (IRBA) of the New Basel Capital Accord allows banks to use their own rating models for the estimation of probabilities of default (PD) as long as the systems meet specified minimum requirements. Statistical theory offers a variety of methods for building and estimation rating models. This chapter gives an overview of these methods. The overview is focused on statistical methods and includes parametric models like linear regression analysis, discriminant analysis, binary response analysis, time-discrete panel methods, hazard models and nonparametric models like neural networks and decision trees. We also highlight the benefits and the drawbacks of the various approaches. We conclude by interpreting the models in light of the minimum requirements of the IRBA.
References
- Altman EI (1968), Financial Indicators, Discriminant Analysis, and the Prediction of Corporate Bankruptcy, Journal of Finance 23 (4), pp 589–609.CrossRefGoogle Scholar
- BIS (2004), International Convergence of Capital Measurement and Capital Standards, Basel Committee on Banking Supervision, June 2004.Google Scholar
- Breiman L, Friedman JH, Olshen RA, Stone SJ (1984), Classification and Regression Trees, Wadsworth, Belmont.Google Scholar
- Chamberlain G (1980), Analysis of Covariance with Qualitative Data, Review of Economic Studies 47, 225–238.CrossRefGoogle Scholar
- Cox DR (1972), Regression Models and Life Tables (with Discussion), Journal of Royal Statistical Society, Series B 34, pp 187–220.Google Scholar
- Greene W (2003), Econometric Analysis, 5th ed., Prentice-Hall, New Jersey.Google Scholar
- Hosmer W, Lemeshow S (2000), Applied Logistic Regression, New York, Wiley.CrossRefGoogle Scholar
- Kass GV (1978), An Exploratory Technique for Investigating Large Quantities of Categorical Data, Applied Statistics 29 (2), pp. 119–127.CrossRefGoogle Scholar