A HMM intensity-based credit risk model and filtering

Robert J. Elliott, Tak Kuen Siu

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

2 Citations (Scopus)

Abstract

In this article we discuss an intensity-based model for portfolio credit risk using a collection of hidden Markov-modulated single jump processes. The model can be viewed as a "dynamic" version of a frailty-based approach to describe the dependent default risk, where firms are exposed to a common hidden dynamic frailty factor described by a hidden Markov chain. Filtering equations and filter-based estimates of the model, in recursive forms, are developed. We also give the joint default probability of reference entities in a credit portfolio as well as the variance dynamics for both observations and hidden states.
Original languageEnglish
Title of host publicationState-space models
Subtitle of host publicationapplications in economics and finance
EditorsYong Zeng, Shu Wu
Place of PublicationNew York
PublisherSpringer, Springer Nature
Pages169-184
Number of pages16
ISBN (Print)9781461477891
Publication statusPublished - 2013
Externally publishedYes

Publication series

NameStatistics and econometrics for finance
PublisherSpringer

Fingerprint Dive into the research topics of 'A HMM intensity-based credit risk model and filtering'. Together they form a unique fingerprint.

Cite this