Methods Matter : p-Hacking and Publication Bias in Causal Analysis in Economics: Comment

Brodeur et al. (2020) study a large number of hypothesis tests from top economic articles and find evidence for p-hacking or publication bias, in particular for articles using DID or IV as causal identification method. We show that a crucial continuity assumption is violated because many collected estimates and standard errors are reported with just a single significant digit. These rounding errors cause bunching of computed z-statistics at exactly 2. We adjust for rounding errors and then find no evidence for p-hacking or publication bias in the DID and pooled data, but evidence remains for IV