I quantitatively evaluate how much of the cross‐sectional return predictive ability of a range of accounting anomalies can be attributed to firm‐specific stock return covariances with market risk factors. Using a novel two‐step regression‐based testing method, I find robust evidence that the risk factor exposures do not explain a meaningful fraction of the time‐series variations in the return predictive coefficients of the anomaly variables. Out‐of‐sample tests further confirm that it is the mispricing component of the accounting anomalies that is mainly responsible for the return predictability.