Defenders of market efficiency argue that anomalies involving long-term abn
ormal returns are not robust to alternative methodologies. We argue that be
cause various methodologies use different weighting schemes, the magnitude
of abnormal returns should differ, and in a predictable manner. Three probl
ems are identified that cause low power in value-weighted three-factor time
series regressions when abnormal returns following managerial actions are
being estimated. We illustrate the sensitivities in the context of the new
issues puzzle as well as with simulations. More generally, multifactor mode
ls as currently used do not, and cannot, test market efficiency. (C) 2000 E
lsevier Science S.A. All rights reserved. JEL classification: G12; G14.