A Unified Approach to Testing for Serial Correlation in Stock Returns.

This article provides a unified approach for testing serial correlation in stock returns. The authors describe a general class of statistics that are linear combinations of consistent estimators of autocorrelations. As special cases, they show that this class captures many of the statistics studied in the recent finance and macroeconomics literature. Using this result, the authors then provide a common perspective on the asymptotic distribution and power of these statistics. Copyright 1994 by University of Chicago Press.