Multi-Regime Nonlinear Capital Asset Pricing Models

Chen, Cathy W. S.; Gerlach, Richard H.; Lin, Ann M. H.

doi:10.2139/ssrn.1410271

Download This Paper

Open PDF in Browser

Add Paper to My Library

Multi-Regime Nonlinear Capital Asset Pricing Models

33 Pages Posted: 27 May 2009

See all articles by Cathy W. S. Chen

Cathy W. S. Chen

Feng Chia University - Department of Statistics; Graduate Institute of Statistics & Actuarial Science, Feng Chia University

Ann M. H. Lin

Feng Chia University

Date Written: April 14, 2009

Abstract

A multiple-regime threshold generalized autoregressive conditionally heteroskedastic capital asset pricing model is introduced. The model captures asymmetric risk through allowing market beta to change discretely between regimes that are driven by market information. Asymmetric volatility and mean equation dynamics are also captured. We confirm the time-varying nature of market risk, in response to changes in the market, and that this discrete time variation can differ across assets. These findings could have important implications for optimising investment decisions: e.g. in risk assessment, portfolio selection and hedging decisions.

Keywords: Asymmetry, Bayesian, CAPM, Time-varying market beta, Markov chain Monte Carlo method, posterior model probability

JEL Classification: C11, C15, C22, C51, C52

Suggested Citation: Suggested Citation

Chen, Cathy W. S. and Gerlach, Richard H. and Lin, Ann MH, Multi-Regime Nonlinear Capital Asset Pricing Models (April 14, 2009). Available at SSRN: https://ssrn.com/abstract=1410271 or http://dx.doi.org/10.2139/ssrn.1410271