Examples of Migration Matrices Models and their Performance in Credit Risk Analysis |
| U. Grzybowskaa, M. Karwańskia and A. Orłowskia,b
a Katedra Informatyki SGGW, Nowoursynowska 159, 02-776 Warszawa, Poland b Instytut Fizyki PAN, al. Lotników 32/46, 02-668 Warszawa, Poland |
| Full Text PDF |
| Credit risk models used in banks are based on probability models for occurrence of default. A vast class of the models used in practice (e.g., Credit Metrics) is based on the notion of intensity. In 1997 Jarrow applied Markov chain approach to analyze intensities. The key problem that arises is the selection of appropriate estimators. Within the Markov approach among the most frequently used estimators of a migration matrix are cohort and duration estimators. Migration matrices can also be obtained with help of statistical longitudinal models (GLMM) in which states (rating classes) in discrete time points are regarded as matched pairs. In this paper we compare Markov chain models and GLMM models and the influence of their application on bank portfolio evaluation. |
| DOI: 10.12693/APhysPolA.121.B-40 PACS numbers: 02.50. Ga, 87.55.N-, 02.10.Yn |