The Random-Walk Hypothesis on the Indian Stock Market

We test the random-walk hypothesis for the Indian stock market by applying three unit root tests with two structural breaks. We find that unit root tests that allow for two structural breaks alone are not able to reject the unit root null; however, a recently developed unit root test that simultaneously accounts for heteroskedasticity and structural breaks finds that the stock indexes are mean reverting. Our results point to the importance of addressing heteroskedasticity when testing for a random walk with high-frequency financial data.