Stress Testing Banks' Credit Risk Using Mixture Vector Autoregressive Models

Fong, Tom; Wong, Chun Shan

doi:10.2139/ssrn.1326833

Download This Paper

Open PDF in Browser

Add Paper to My Library

Stress Testing Banks' Credit Risk Using Mixture Vector Autoregressive Models

23 Pages Posted: 15 Jan 2009

See all articles by Tom Fong

Chun Shan Wong

affiliation not provided to SSRN

Date Written: October 13, 2008

Abstract

This paper estimates macroeconomic credit risk of banks' loan portfolio based on a class of mixture vector autoregressive models. Such class of models can differentiate distributions of default rates and macroeconomic conditions for different market situations and can capture their dynamics evolving over time, including the feedback effect from an increase in fragility back to the macroeconomy. These extensions can facilitate the evaluation of credit risks of loan portfolio based on different credit loss distributions.

Keywords: Stress test, Hong Kong banking, credit risk, mixture autoregressive models, macroeconomic shocks, value-at-risk

JEL Classification: C15, C32, C53, E37, G21

Suggested Citation: Suggested Citation

Fong, Tom and Wong, Chun Shan, Stress Testing Banks' Credit Risk Using Mixture Vector Autoregressive Models (October 13, 2008). Available at SSRN: https://ssrn.com/abstract=1326833 or http://dx.doi.org/10.2139/ssrn.1326833