Bayesian default probability models

Petra Andrlikova

No 2014/14, Working Papers IES from Charles University Prague, Faculty of Social Sciences, Institute of Economic Studies

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).

Keywords: default probability; bayesian analysis; logistic regression; goodness-of-fit (search for similar items in EconPapers)
JEL-codes: C11 C51 C52 G10 (search for similar items in EconPapers)
Pages: 20pages
Date: 2014-04, Revised 2014-04
New Economics Papers: this item is included in nep-ecm and nep-rmg
References: Add references at CitEc
Citations:

Downloads: (external link)
http://ies.fsv.cuni.cz/sci/publication/show/id/5088/lang/cs (application/pdf)
Our link check indicates that this URL is bad, the error code is: 404 Not Found (http://ies.fsv.cuni.cz/sci/publication/show/id/5088/lang/cs [301 Moved Permanently]--> https://ies.fsv.cuni.cz/sci/publication/show/id/5088/lang/cs)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:fau:wpaper:wp2014_14

Access Statistics for this paper

More papers in Working Papers IES from Charles University Prague, Faculty of Social Sciences, Institute of Economic Studies Contact information at EDIRC.
Bibliographic data for series maintained by Natalie Svarcova ().