Autor: |
|
Typ: |
IES Working Papers |
Rok: |
2014 |
Číslo: |
14 |
ISSN / ISBN: |
|
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
|