Abstract:
We provide data and code that successfully reproduces nearly all crosssectional stock return predictors. Unlike most metastudies, we carefully examine the original papers to determine whether our predictability tests should produce t-stats above 1.96. For the 180 predictors that were clearly significant in the original papers, 98% of our reproductions find t-stats above 1.96. For the 30 predictors that had mixed evidence, our reproductions find t-stats of 2 on average. We include an additional 105 characteristics and 945 portfolios with alternative rebalancing frequencies to nest variables used in other metastudies. Our data covers all portfolios in Hou, Xue and Zhang (2017); 98% of the portfolios in McLean and Pontiff (2016); 90% of the characteristics from Green, Hand, and Zhang (2017); and 90% of the firm-level predictors in Harvey, Liu, and Zhu (2016) that use widelyavailable data.
