Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/102563 
Autor:innen: 
Erscheinungsjahr: 
2014
Schriftenreihe/Nr.: 
IES Working Paper No. 14/2014
Verlag: 
Charles University in Prague, Institute of Economic Studies (IES), Prague
Zusammenfassung: 
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).
Schlagwörter: 
default probability
bayesian analysis
logistic regression
goodness-of-fit
JEL: 
C11
C51
C52
G10
Dokumentart: 
Working Paper

Datei(en):
Datei
Größe
449.46 kB





Publikationen in EconStor sind urheberrechtlich geschützt.