This article investigates the finite-sample performance of a modified Box-P
ierce a statistic (Q*) for testing that financial time series are uncorrela
ted without assuming statistical independence. The finite-sample rejection
probabilities of the (Q* test under the null and its power are examined in
experiments using time series generated by an MA(1) process where the error
s are generated by a GARCH (1,1) model and by a long memory stochastic vola
tility model. The tests are applied to daily currency returns.