DefaultRisk.com the web's biggest credit risk modeling resource. | 
|
|
|
| Bayesian Inference for Issuer Heterogeneity in Credit Ratings Migration by Ashay Kadam of City University, London, and February 7, 2007 Abstract: We explore sources of heterogeneity in rating migration behavior using a continuous time Markov chain. Working in continuous time circumvents the embedding problem, mitigates the censoring effect and facilitates term structure modelling with arbitrary prediction horizons. By adopting a Bayesian estimation procedure we are able to mitigate the problems arising from data sparsity. We estimate for each issuer profile its own continuous time Markov chain generator. Using the Moody's corporate bond default database we identify significant country and industry effects on the determination of default intensity and conditional transition probabilities in general. We tabulate and compare these quantities for different issuer profiles to assess the heterogeneity in the sample. The transition probability matrices for different issuer profiles can be quite different from each other, as demonstrated by the Jafry-Schuermann mobility metric. Using the CreditRisk+ framework, and a sample credit portfolio, we show that ignoring heterogeneity can give erroneous estimates of VAR and a misleading picture of the risk capital. JEL Classification: C11, C13, C41, G12. Keywords: Credit risk, Risk Capital, Markov Chains, Bayesian Inference, Heterogeneity. Previously titled: Heterogeneity in Ratings Migration Books Referenced in this Paper: (what is this?)
Download paper (361K PDF) 48 pages
[Home] [Other Credit Risk Papers]  |   
|
Please contact me with problems or suggestions. |
