45 Pages Posted: 5 Dec 2017 Last revised: 7 Dec 2019
Date Written: December 6, 2019
What distribution best characterizes the time series and cross section of individual stock returns? To answer this question, we estimate the degree of cross-sectional return skewness relative to a benchmark that nests many models considered in the literature. We find that cross-sectional skewness in monthly returns far exceeds what this benchmark model predicts. However, cross-sectional skewness in long-run returns in the data is substantially below what the model predicts. We show that fat-tailed idiosyncratic events appear to be necessary to explain skewness in the data.
Keywords: rare events, jumps, idiosyncratic volatility, power law
JEL Classification: G11, G12
Suggested Citation: Suggested Citation