摘要：Using 16 OECD stock price indices data, this paper revisits the random walk hypothesis by inspecting the degree of persistence of stock prices. We adopt two recently developed econometric procedures, due to Hansen (1999) and Romano and Wolf (2001), in order to estimate 95% confidence intervals for the sum of the AR coefficients in AR representations of international stock prices. Confidence intervals provide much more information than knowing whether the null hypothesis of a unit root can be rejected or not. They serve as a measure of sampling uncertainty and describe the range of models that are consistent with the observed data. The results convincingly support the view that the stock price indices in the OECD countries are highly persistent. The high persistence in the OECD stock price indices provides strong evidence for the random walk hypothesis
