Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/102563
Authors: 
Andrlíková, Petra
Year of Publication: 
2014
Series/Report no.: 
IES Working Paper 14/2014
Abstract: 
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).
Subjects: 
default probability
bayesian analysis
logistic regression
goodness-of-fit
JEL: 
C11
C51
C52
G10
Document Type: 
Working Paper
Appears in Collections:

Files in This Item:
File
Size
449.46 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.