Footnote:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments May 22, 2002 erstellt
Description:
Whereas the existing literature focuses on the relation between weighting schemes and abnormal portfolio return metrics, this study extends the literature and investigates the relation between weighting schemes and raw portfolio return metrics. We show that the equal-weight portfolio return metric systematically yields higher estimates of portfolio returns for event samples than the value-weight portfolio return metric. We also demonstrate that value-weight portfolio return metric can be a biased estimator of the counterpart of the population. These results imply that the commonly used testing procedure based on the matching portfolio method and the Fama-French three factor regression can produce misleading inferences. Several remedies are proposed in this study