Low statistical power in biomedical science: a review of three human research domains
Abstract
Studies with low statistical power increase the likelihood that a statistically significant finding represents a false positive result. We conducted a review of meta-analyses of studies investigating the association of biological, environmental or cognitive parameters with neurological, psychiatric and somatic diseases, excluding treatment studies, in order to estimate the average statistical power across these domains. Taking the effect size indicated by a meta-analysis as the best estimate of the likely true effect size, and assuming a threshold for declaring statistical significance of 5%, we found that approximately 50% of studies have statistical power in the 0-10% or 11-20% range, well below the minimum of 80% that is often considered conventional. Studies with low statistical power appear to be common in the biomedical sciences, at least in the specific subject areas captured by our search strategy. However, we also observe evidence that this depends in part on research methodology, with candidate gene studies showing very low average power and studies using cognitive/behavioural measures showing high average power. This warrants further investigation.
Related
- Efficacy of statistical and design interventions for improving reproducibility in biomedical research
- Facilitating Valid Statistical Inference in Biomedical Image Synthesis
- Developing an inclusive research (methods) strategy for the Manchester Biomedical Research Centre and Clinical Research Facility
- From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents
- PromptBio: An Agentic Platform for End-to-End Computational Biomedical Research
BibTeX
@article{dumasmallet2026statistical,
title = {{Low statistical power in biomedical science: a review of three human research domains}},
author = {Estelle Dumas-Mallet and Katherine S. Button and Thomas Boraud and Francois Gonon and Marcus R. Munafò},
journal = {Royal Society Open Science},
year = {2026},
month = nov,
doi = {10.1098/rsos.160254},
url = {https://hal.science/hal-05853262v1},
note = {CC BY},
}
RIS
TY - JOUR
TI - Low statistical power in biomedical science: a review of three human research domains
AU - Estelle Dumas-Mallet
AU - Katherine S. Button
AU - Thomas Boraud
AU - Francois Gonon
AU - Marcus R. Munafò
PY - 2026
DA - 2026/11/05
JO - Royal Society Open Science
DO - 10.1098/rsos.160254
UR - https://hal.science/hal-05853262v1
AB - Studies with low statistical power increase the likelihood that a statistically significant finding represents a false positive result. We conducted a review of meta-analyses of studies investigating the association of biological, environmental or cognitive parameters with neurological, psychiatric and somatic diseases, excluding treatment studies, in order to estimate the average statistical power across these domains. Taking the effect size indicated by a meta-analysis as the best estimate of the likely true effect size, and assuming a threshold for declaring statistical significance of 5%, we found that approximately 50% of studies have statistical power in the 0-10% or 11-20% range, well below the minimum of 80% that is often considered conventional. Studies with low statistical power appear to be common in the biomedical sciences, at least in the specific subject areas captured by our search strategy. However, we also observe evidence that this depends in part on research methodology, with candidate gene studies showing very low average power and studies using cognitive/behavioural measures showing high average power. This warrants further investigation.
SN - 2054-5703
SN - 2054-5703
ER -