Unit Root Hypothesis in the Presence of Stochastic Volatility, a Bayesian Analysis

This paper investigates the impact of stochastic volatility on the Dickey-Fuller unit root test. Monte Carlo simulations show that the test size is seriously distorted if nonstationary stochastic volatility is ignored. To improve the performance of the test, we propose a Bayesian test for unit root that is robust in the presence of stationary and nonstationary stochastic volatility. The finite sample property of the proposed test statistic is evaluated using Monte Carlo studies. Applying the developed method, we test the policy effect of the Split Share Structure Reform, which is an important milestone for the development of the emerging stock market in China.