P-hacking, data type and data-sharing policy

In this paper, we examine the relationship between p-hacking and datasharing policies for published articles. We collect 38,876 test statistics from 1,106 articles published in leading economic journals between 2002-2020. While a data-sharing policy increases the provision of research data to the community, we find a well-estimated null effect that requiring authors to share their data at the time of publication does not alter the presence of p-hacking. Similarly, articles that use hard-to-access administrative data or third-party surveys, as compared to those that use easier-to-access (e.g., own-collected) data are not different in their p-hacking extent. Voluntary provision of data by authors on their homepages offers no evidence of reduced p-hacking.