The harmonic mean <i>p</i>-value for combining dependent tests.
Wilson DJ. · 2019
Read The harmonic mean <i>p</i>-value for combining dependent tests. by Wilson DJ. (2019) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc6347718.txt.
Description
Wilson introduces the harmonic mean p-value for combining dependent tests. His paper appeared in the Proceedings of the National Academy of Sciences. Big datasets invite thousands of tests at once. The usual Bonferroni fix is strict and wasteful. It over-penalizes large test counts, he argues. That discourages broad, exploratory analysis.
The new measure blends p-values by their harmonic mean. Its roots lie in Bayesian model averaging. It keeps the standard false positive rate under control. At the same time it gains statistical power. The paper lists the measure's useful properties. It applies across many kinds of study. Genetics is a prime example field. The author offers it as a new lens on large-scale testing.
Catalog record
| CREATOR | Wilson DJ. |
|---|---|
| YEAR | 2019 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 32 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |