The alternative Durbin-Watson test. An assessment of Durbin and Watson's choice of test statistic

This paper examines Durbin and Watson's (1950) choice of test statistic for their test of first- 0order autoregressive regression disturbances. Attention is focused on an alternative statistic, d'. Theoretical and empirical power properties of the d' test are compared with those of the Durbin-Watson test. The former is found to be locally best invariant while the latter is approximately locally best invariant. The d' test is also found to be more powerful than its counterpart against negative autocorrelation and for small values of the autocorrelation coefficient against positive autocorrelation. Selected bounds for significance points of d' are tabulated.