English

Detecting p-hacking

Econometrics 2022-05-13 v5 General Economics Economics

Abstract

We theoretically analyze the problem of testing for pp-hacking based on distributions of pp-values across multiple studies. We provide general results for when such distributions have testable restrictions (are non-increasing) under the null of no pp-hacking. We find novel additional testable restrictions for pp-values based on tt-tests. Specifically, the shape of the power functions results in both complete monotonicity as well as bounds on the distribution of pp-values. These testable restrictions result in more powerful tests for the null hypothesis of no pp-hacking. When there is also publication bias, our tests are joint tests for pp-hacking and publication bias. A reanalysis of two prominent datasets shows the usefulness of our new tests.

Keywords

Cite

@article{arxiv.1906.06711,
  title  = {Detecting p-hacking},
  author = {Graham Elliott and Nikolay Kudrin and Kaspar Wuthrich},
  journal= {arXiv preprint arXiv:1906.06711},
  year   = {2022}
}