Testing the Random Walk Hypothesis: Power versus Frequency of Observation

Power functions of tests of the random walk hypothesis versus stationary first order autoregressive alternatives are tabulated for samples of fixed span but various frequencies of observation. For a t-test and normalized test, power is found to depend, for a substantial range of parameter values, more on the span of the data in time than on the number of observations. For a runs test, power rapidly declines as the number of observations is increased beyond a certain point.

JEL Classification: 211, 313

Keywords: Random walk, Unit roots, Power function, Efficient markets hypothesis