Menu Expand

Die Bewertung und der Vergleich von Kreditausfall-Prognosen

Cite JOURNAL ARTICLE

Style

Krämer, W. Die Bewertung und der Vergleich von Kreditausfall-Prognosen. Credit and Capital Markets – Kredit und Kapital, 36(3), 395-410. https://doi.org/10.3790/ccm.36.3.395
Krämer, Walter "Die Bewertung und der Vergleich von Kreditausfall-Prognosen" Credit and Capital Markets – Kredit und Kapital 36.3, 2003, 395-410. https://doi.org/10.3790/ccm.36.3.395
Krämer, Walter (2003): Die Bewertung und der Vergleich von Kreditausfall-Prognosen, in: Credit and Capital Markets – Kredit und Kapital, vol. 36, iss. 3, 395-410, [online] https://doi.org/10.3790/ccm.36.3.395

Format

Die Bewertung und der Vergleich von Kreditausfall-Prognosen

Krämer, Walter

Credit and Capital Markets – Kredit und Kapital, Vol. 36 (2003), Iss. 3 : pp. 395–410

Additional Information

Article Details

Author Details

Walter Krämer, Dortmund

References

  1. Blochwitz, S./Liebig, Th./Nyberg, M. (2000): „Benchmarking Deutsche Bundesbank’s, default risk model, the KMV private firm model and common financial ratios for German cooperations.“ Bundesbank-Diskussionspapier.  Google Scholar
  2. Brier G. W. (1950): „Verification of forecasts expressed in terms of probability.“ Monthly Weather Review 78, 1-3.  Google Scholar
  3. DeGroot, M./Fienberg, S. (1983): „The comparison and evaluation of forecasters.“ The Statistician 32, 12-23.  Google Scholar
  4. DeGroot, M./Eriksson, E. A. (1985): „Probability forecasting, stochastic dominance, and the Lorenz curve,“ in: S. S. Gupta und J. O. Berger (Hrsg): Statistical decision theory and related topics III, Vol 1, New York (Academic Press), S. 291-314.  Google Scholar
  5. Engelmann, B./Hayden, E./Tasche, D. (2003): „Testing rating accuracy.“ Risk 16, 82-86.  Google Scholar

Abstract

Evaluation and Comparison of Default Forecasts in the Rating Industry

This article shows that probability forecasts may in many respects be ranked in terms of quality. It makes clear in particular that correspondence of the predicted default probability and the relative frequency of the actual defaults is no quality guarantee in itself. The latter would only be the case when the predicted default probability is near 0% and near 100%. In addition, this article discusses various scalar measures permitting a ranking of the forecasting quality.