Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Empowering research: statistical power in general practice research

N Fox1, N Mathers

  • 1Institute of General Practice and Primary Care, School of Health and Related Research, University of Sheffield, UK.

Family Practice
|August 1, 1997
PubMed
Summary

General practice research often lacks adequate statistical power, with a median power of 0.71, falling short of the conventional 0.8. This means studies may miss real effects, highlighting the need for improved power calculations and reporting.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Identifying barriers to the sustainable control of gastro-intestinal nematodes in sheep: a social science perspective.

Animal : an international journal of animal bioscience·2025
Same author

Antibody landscape of C57BL/6 mice cured of B78 melanoma via immunotherapy.

bioRxiv : the preprint server for biology·2023
Same author

Scurvy: a forgotten cause of purpuric rash.

Clinical and experimental dermatology·2021
Same author

Positive pleural fluid RT-PCR for virus detection in SARS-CoV-2 pneumonia.

QJM : monthly journal of the Association of Physicians·2020
Same author

Enriched environment exposure accelerates rodent driving skills.

Behavioural brain research·2019
Same author

C-Reactive Protein Levels and the Risk of Incident Cardiovascular and Cerebrovascular Events in Patients with Obstructive Sleep Apnea.

Lung·2019

Area of Science:

  • Medical Research
  • Biostatistics
  • General Practice

Background:

  • Statistical power is crucial for detecting true effects in research.
  • A conventional benchmark for adequate statistical power is 0.8.
  • Increasing sample size is a primary method to enhance statistical power.

Purpose of the Study:

  • To evaluate the statistical power of research published in general practice.
  • To determine if general practice studies meet the conventional power benchmark.

Main Methods:

  • Analysis of 1422 statistical tests from 85 quantitative original papers.
  • Papers were sourced from the British Journal of General Practice.

Main Results:

  • The median statistical power was 0.71, indicating a 71% chance of rejecting a false null hypothesis.

Related Experiment Videos

  • Only 44% of studies achieved the recommended power of 0.8 or higher.
  • A significant portion of studies (25%) had a lower probability of detecting a false null hypothesis than a coin toss.

    • Conclusions:

    • General practice research demonstrates higher power than some other fields but still falls below the 0.8 convention.
    • Insufficient statistical power risks overlooking genuine effects.
    • Recommendations emphasize pre-research power calculations and transparent reporting of results.