The Idiosyncratic Volatility Puzzle: A Time-Specific Anomaly

Abstract

Given the availability of daily data over 1926-1962, it is surprising that there is no research examining the idiosyncratic volatility (IV) puzzle over this early period. This paper conducts an out-of-sample test on the IV phenomenon. We find that the negative relation between IV and expected returns only exists during the period 07/1963-12/1989, implying that the puzzle may be a result of data snooping bias. The result on time-special anomaly is robust for different sorting breakpoints and alternative measure of idiosyncratic volatility. Infrequent trading cannot account for the low average returns of stocks with high idiosyncratic volatility. With a striking contrast, the involving of short-term return reversals eliminates this dilemma.