A Comparison of the Robustness of Several Tests of Short Memory to Autocorrelated Errors

In this paper we consider the robustness to error autocorrelation of four stationarity tests. The size and power properties of these tests are investigated by simulation. Size is improved by using fixed-b critical values to account for the number of lags used in long-run variance estimation. Lo’s MR/S test is not very robust. Choi’s LM test has excellent robustness properties but this comes at some cost in power; it is not as powerful as the KPSS test or the rescaled variance (V/S) test.