The Shrinking Space for Anomalies

Abstract

Existing literature has documented a number of cross-sectional stock return predictive patterns or the so-called anomalies. This paper examines two important issues: are the anomalies pervasive in different stock samples and do factor models provide valid inferences on anomalous returns? First, by shrinking the stock space along the dimension of predictive variable, we show that the BM and net stock issues effects are pervasive among different stock samples, whereas the size, momentum, and illiquidity effects are driven mainly by stocks on the long side, and the idiosyncratic olatility, accrual, capital expenditure, and sales growth effects mainly by stocks on the short side. Second, we provide evidence that commonly used factor models have limited explanatory power of stock returns and thus may offer invalid inference on abnormal returns. Restricting to the stock sample where the 4-factor model adequately explains the size, BM and momentum effects, we show that only the idiosyncratic volatility, accrual, and net stock issues effects have significant anomalous returns.