This paper evaluates skewness in the cross-section of stock returns in light of predictions from a well-known class of models. Cross-sectional skewness in monthly returns far exceeds what the standard lognormal model of returns would predict. However, skewness in long-run returns substantially understates what the lognormal model would predict. Nonstationary share dynamics imply a breakdown in the distinction between market and idiosyncratic risk in the lognormal model. We present an alternative model that matches the skewness in the data and implies stationary wealth shares. In this model, idiosyncratic risk is the primary driver of growth in the economy.
We thank Hendrik Bessembinder, John Campbell, Marco Grotteria, Nishad Kapadia, Yapai Zhang, and seminar participants at the Wharton School for helpful comments. The views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research.
Sangmin S Oh & Jessica A Wachter & Hui Chen, 2022. "Cross-Sectional Skewness," The Review of Asset Pricing Studies, vol 12(1), pages 155-198.