# Permutation P-values Should Never Be Zero: Calculating Exact P-values When Permutations Are Randomly Drawn

*Source* · `src-phipson-2010-permutation-p-values` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Belinda Phipson, Gordon K. Smyth |
| venue | Statistical Applications in Genetics and Molecular Biology 9(1) |
| date | 2010-10-31 |
| url | https://www.degruyterbrill.com/document/doi/10.2202/1544-6115.1585/html |
| doi | 10.2202/1544-6115.1585 |
| accessed | 2026-11-02 |

## Notes

On p-values from randomly drawn permutations: counting the observed statistic among the draws gives (b + 1) / (m + 1), which cannot be zero, so with m draws the smallest attainable p-value is 1 / (m + 1). The paper prints a Monte Carlo p-value at that floor as an inequality.

## Citation

Belinda Phipson, Gordon K. Smyth (2010-10-31). *Permutation P-values Should Never Be Zero: Calculating Exact P-values When Permutations Are Randomly Drawn*. Statistical Applications in Genetics and Molecular Biology 9(1) https://www.degruyterbrill.com/document/doi/10.2202/1544-6115.1585/html

---
Provenance: created in run `2026-11-02-es-v5-revision`.