On the conditional performance of the IVOL anomaly

Abstract

This paper proposes that the well-known idiosyncratic volatility (IVOL) puzzle is partly due to an overconditioning bias in IVOL estimates when there exists nonlinearity between stock and factor returns. We analytically derive the overconditioning bias when beta and IVOL are contemporaneously estimated using daily returns. To mitigate the estimation bias, we employ a conditional factor model, as in Avramov and Chordia (2006), to estimate systematic risk exposure and IVOL. Our empirical results show that the conditional IVOL estimates do not imply a negative return premium when firm fundamentals are used as conditioning variables, and the associated conditional factor-adjusted alpha is much smaller than the original IVOL puzzle. Our findings are robust in the U.S. and Chinese stock markets.