Arbeitspapier
Bayesian default probability models
This paper proposes a methodology for default probability estimation for low default portfolios, where the statistical inference may become troublesome. The author suggests using logistic regression models with the Bayesian estimation of parameters. The piecewise logistic regression model and Box-Cox transformation of credit risk score is used to derive the estimates of probability of default, which extends the work by Neagu et al. (2009). The paper shows that the Bayesian models are more accurate in statistical terms, which is evaluated based on Hosmer-Lemeshow goodness of fit test, Hosmer et al. (2013).
- Sprache
-
Englisch
- Erschienen in
-
Series: IES Working Paper ; No. 14/2014
- Klassifikation
-
Wirtschaft
Bayesian Analysis: General
Model Construction and Estimation
Model Evaluation, Validation, and Selection
General Financial Markets: General (includes Measurement and Data)
- Thema
-
default probability
bayesian analysis
logistic regression
goodness-of-fit
- Ereignis
-
Geistige Schöpfung
- (wer)
-
Andrlíková, Petra
- Ereignis
-
Veröffentlichung
- (wer)
-
Charles University in Prague, Institute of Economic Studies (IES)
- (wo)
-
Prague
- (wann)
-
2014
- Handle
- Letzte Aktualisierung
-
10.03.2025, 11:44 MEZ
Datenpartner
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Objekttyp
- Arbeitspapier
Beteiligte
- Andrlíková, Petra
- Charles University in Prague, Institute of Economic Studies (IES)
Entstanden
- 2014