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

Dieses Objekt wird bereitgestellt von:
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

Ähnliche Objekte (12)