Detail publikace

Bayesian default probability models

Autor: Petra Andrlíková MSc.,
Typ: IES Working Papers
Rok: 2014
Číslo: 14
Publikováno v: IES Working Papers 14/2014
Místo vydání: Prague
Klíčová slova: default probability, bayesian analysis, logistic regression, goodness-of-fit
JEL kódy: C11, C51, C52, G10
Citace: Andrlíková P. (2014). “Bayesian default probability models” IES Working Paper 14/2014. IES FSV. Charles University.
Abstrakt: 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).
Ke stažení: WP_2014_14_Andrlikova


McKinsey & Company
Moneta Money Bank