The efficient market hypothesis re-visited: new evidence from 100 US firms

In this paper, we test the efficient market hypothesis for 100 US firms listed on the New York Stock Exchange. To test the unit root null hypothesis, we develop a generalized autoregressive heteroskedasticity (GARCH) model that not only caters for the GARCH errors but also allows for two endogenous structural breaks in the data series. We study the size and power properties of the proposed GARCH structural break unit root test and find that it statistically performs well in finite samples. We find that only 22% of firms have a stationary stock price series.