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

Beyond classical meta-analysis: can inadequately reported studies be included?

Chris Robertson1, Nik Ruzni Nik Idris, Peter Boyle

  • 1Department of Statistics and Modelling Science, University of Strathclyde, 26 Richmond Street, Glasgow, Scotland G1 1XH, UK. chris@stams.strath.ac.uk

Drug Discovery Today
|October 27, 2004
PubMed
Summary

High-quality data is crucial for meta-analysis. Advanced methods like regression and imputation can incorporate diverse study types, enhancing treatment effect precision while requiring careful sensitivity analysis.

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

Tocilizumab versus sarilumab among adults hospitalised with COVID-19: target trial emulation across England and Scotland.

Nature communications·2026
Same author

Bivalent RSV prefusion vaccine effectiveness against hospitalisation in older adults: meta-analysis of case-control studies in England, Wales, Scotland, and Northern Ireland.

The Lancet regional health. Europe·2026
Same author

On the simultaneous inference of susceptibility distributions and intervention effects from epidemic curves.

Epidemics·2026
Same author

Study protocol: Effectiveness of the maternal RSVpreF vaccine by virus type.

Wellcome open research·2026
Same author

Effectiveness of the maternal RSVpreF vaccine against severe disease in infants in Scotland, UK: a national, population-based case-control study and cohort analysis.

The Lancet. Infectious diseases·2025
Same author

RSV Vaccination Programme for Older Adults: A Scotland-Wide Study on RSVpreF Vaccine Safety.

Vaccines·2025

Area of Science:

  • Biostatistics
  • Clinical Trial Analysis
  • Pharmacoeconomics

Background:

  • Classical meta-analysis relies on complete, high-quality data from clinical trials.
  • Incomplete data on variability and treatment effects necessitates advanced analytical approaches.
  • Incorporating diverse study designs beyond randomized placebo-controlled trials is challenging but beneficial.

Purpose of the Study:

  • To explore the utility of imputation and regression methods in meta-analysis.
  • To assess the impact of including non-randomized and comparator-controlled studies on treatment effect estimation.
  • To demonstrate how diverse study inclusion enhances precision in meta-analysis.

Main Methods:

  • Utilized imputation techniques to handle incomplete study data.

Related Experiment Videos

  • Employed regression models to incorporate non-randomized single-arm studies and comparator-controlled studies.
  • Conducted a sensitivity analysis to validate findings.

    • Main Results:

    • Inclusion of non-randomized and comparator-controlled studies had minimal impact on placebo-based treatment effect estimates.
    • Incorporating additional study types significantly increased the precision of treatment effect estimates compared to baseline.
    • Multiple imputation techniques successfully increased the number of included studies and overall precision.

    Conclusions:

    • Advanced statistical methods enable broader inclusion of clinical trial data in meta-analysis.
    • The precision of treatment effect estimation can be substantially improved by incorporating diverse study designs.
    • Robust sensitivity analyses are essential when utilizing complex meta-analytic techniques.