Publication Bias and the Cross-Section of Stock Returns

We develop an estimator for publication bias adjusted returns and apply it to 156 replications of published long-short portfolio returns. Bias-adjusted returns are only 12.3% smaller than sample returns with a standard error of 1.7 percentage points. The small bias comes from the dispersion of returns across predictors, which is too large to be accounted for by data-mined noise. Our estimate is free of economic effects and small sample noise that cloud out-of-sample tests. The bias is much smaller than post-publication decay (p-value < 0.0001), suggesting mispricing is important. Our results offer a different perspective on recent papers that find most published predictors are likely false