Asymmetric Smooth Transition Quantile Capital Asset Pricing Model with Time-Varying Effect

• Main Authors: Chang-Zih Lin, 林昶字
• Other Authors: Cathy Chen
• Format: Others
• Language: en_US
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/61705253078409625128

碩士 === 逢甲大學 === 統計與精算所 === 98 === Capital asset pricing model (CAPM) has become a fundamental tool in finance for assessing the cost of capital, risk management, portfolio diversification and other financial assets. It is generally believed that the risks of assets should change over time or vary with the market returns. In this study, we propose a time-varying market risk (beta) for CAPM which adds a smooth transition function as a regime switching function, and fit a GARCH model in variance equation to consider the dynamic volatility. We use the quantile regression technique to investigate the change of market risk under various market conditions. We introduce a smooth transition CAPM that can capture nonlinear behavior both in the mean and volatility in all quantile levels. The parameter estimation is within the Bayesian framework. We employ three of stocks from the Dow Jones Industrial Stocks to demonstrate our proposed model. We use deviance information criterion (DIC) in a comparison of our proposed model with the previous models. Our study shows that the proposed model is more appropriate for the data. The proposed model is more general and its coefficients have greater flexibility with a smooth transition function.