English

The Power of Tests for Detecting $p$-Hacking

Econometrics 2025-08-12 v4

Abstract

A flourishing empirical literature investigates the prevalence of pp-hacking based on the distribution of pp-values across studies. Interpreting results in this literature requires a careful understanding of the power of methods for detecting pp-hacking. We theoretically study the implications of likely forms of pp-hacking on the distribution of pp-values to understand the power of tests for detecting it. Power can be low and depends crucially on the pp-hacking strategy and the distribution of true effects. Combined tests for upper bounds and monotonicity and tests for continuity of the pp-curve tend to have the highest power for detecting pp-hacking.

Cite

@article{arxiv.2205.07950,
  title  = {The Power of Tests for Detecting $p$-Hacking},
  author = {Graham Elliott and Nikolay Kudrin and Kaspar Wüthrich},
  journal= {arXiv preprint arXiv:2205.07950},
  year   = {2025}
}

Comments

Some parts of this paper are based on material in earlier versions of our arXiv working paper "Detecting p-hacking" (arXiv:1906.06711), which were not included in the final published version (Elliott et al., 2022, Econometrica)

R2 v1 2026-06-24T11:19:08.274Z