Testing Mean Reversion in Stock Market Volatility

This paper presents a comprehensive study of continuous time GARCH modeling with the thin-tailed normal and the fat-tailed Student-t and generalized error distributions. The paper measures the degree of mean reversion in stock return volatility based on the relationship between discrete time GARCH and continuous time diffusion models. The convergence results based on the aforementioned distribution functions are shown to have similar implications for testing mean reversion in stochastic volatility. Alternative models are compared in terms of their ability to capture mean-reverting behavior of stock return volatility. The empirical evidence obtained from several stock market indices indicates that the conditional variance, log-variance, and standard deviation of stock market returns are pulled back to some long-run average level over time