The results of academic and practitioners’ event studies are often translated from excess log returns into excess dollar returns. The prior literature argues for a difference between the statistical significance of excess log returns and that of excess dollar returns. In contrast, we show analytically and using simulations that specifying event study hypotheses in terms of excess dollar returns is equivalent to specifying them in terms of excess log returns. The prior literature’s result was due to a bias in the estimator of expected excess dollar returns, an incorrect assumption that it is approximately normally distributed, and a misapplication of the delta method.
Semiannual reporting threatens enforcement of insider trading
CRA’s Swati Kanoria has co-authored a new article with Douglas Miller and Val Bianchi-Demicheli of Boies Schiller Flexner LLP, in which they assess how the...