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

Power analysis for random-effects meta-analysis.

Dan Jackson1, Rebecca Turner1

  • 1MRC Biostatistics Unit, Cambridge, UK.

Research Synthesis Methods
|April 6, 2017
PubMed
Summary
This summary is machine-generated.

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

Navigating the Spectrum of Inflammatory Myocardial and Pericardial Syndromes: A Contemporary Approach to Diagnosis and Management.

Journal of cardiac failure·2026
Same author

Large-scale, real-world collection of refractive outcomes after cataract surgery through patient-mediated mobile photography.

Eye (London, England)·2026
Same author

Evaluation of Routine Clinical Deployment of an Autonomous Artificial Intelligence Assistant for Cataract Follow-Up in the National Health Service.

Clinical ophthalmology (Auckland, N.Z.)·2026
Same author

Views of People With Psychosis About Algorithm-Based Relapse Prediction and Data Sharing: Qualitative Study.

Journal of medical Internet research·2026
Same author

A systematic review of antimicrobial stewardship education for undergraduate students in medicine, nursing, pharmacy, dentistry, veterinary science and midwifery using COM-B framework.

JAC-antimicrobial resistance·2026
Same author

Cure Models: What is Meant by a Survival 'Plateau', and Do Experts Agree on What Constitutes One?

PharmacoEconomics·2025
Same journal

Doubly robust augmented weighting estimators for the analysis of externally controlled single-arm trials and unanchored indirect treatment comparisons.

Research synthesis methods·2026
Same journal

Prompt engineering of large language models for paper screening in medical meta-analyses and systematic reviews: A prospective comparative study - CORRIGENDUM.

Research synthesis methods·2026
Same journal

Evaluating the accuracy and speed of eight deduplication tools: A comparative study.

Research synthesis methods·2026
Same journal

A comparison of preprint search aggregators: comprehensive identification of preprints in the information retrieval stage of evidence syntheses.

Research synthesis methods·2026
Same journal

Meta-research on key metrics of preregistered scoping reviews.

Research synthesis methods·2026
Same journal

Facilitators and barriers to engaging patient partners in knowledge syntheses: A stage-based approach.

Research synthesis methods·2026
See all related articles

Random-effects meta-analyses may not always increase statistical power compared to individual studies. At least five studies are typically needed for meta-analyses to achieve greater power, challenging common assumptions.

Area of Science:

  • Biostatistics
  • Medical Research Methodology

Background:

  • Meta-analysis is popular for its perceived increase in statistical power over individual studies.
  • This is true for fixed-effect models, but random-effects models introduce complexities.

Purpose of the Study:

  • To develop methods for assessing the statistical power of random-effects meta-analyses.
  • To compare the power of meta-analyses with the average power of their contributing individual studies.

Main Methods:

  • Developed analytical methods for power assessment in random-effects meta-analysis.
  • Applied these methods to 1991 meta-analyses from the Cochrane Database of Systematic Reviews.

Main Results:

  • Random-effects meta-analyses often require five or more studies to consistently achieve higher power than individual studies.
Keywords:
cochraneempirical evaluationpower calculationsrandom-effects meta-analysis

Related Experiment Videos

  • Statistical inference is challenging and less worthwhile with very few studies in random-effects models.

    • Conclusions:

    • The assumption that meta-analysis always increases power is challenged by findings for random-effects models.
    • Few studies in a meta-analysis may diminish, rather than enhance, statistical power.