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

Modelling multivariate outcomes in hierarchical data, with application to cluster randomised trials.

Rebecca M Turner1, Rumana Z Omar, Simon G Thompson

  • 1MRC Biostatistics Unit, Institute of Public Health, Robinson Way, Cambridge CB2 2SR, UK. rebecca.turner@mrc-bsu.cam.ac.uk

Biometrical Journal. Biometrische Zeitschrift
|July 19, 2006
PubMed
Summary

This study introduces a flexible Bayesian modeling strategy for analyzing multiple outcomes in cluster randomized trials. The approach effectively estimates intervention effects and correlations, offering advantages over classical methods.

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

Cefazolin for Methicillin-Susceptible <i>Staphylococcus aureus</i> Bacteremia.

The New England journal of medicine·2026
Same author

Observational study of predictors and outcomes of lung cancer in never-smokers in the UK (OLIVE): study protocol.

BMJ open respiratory research·2026
Same author

Bayesian analysis in confirmatory clinical trials: A narrative review and discussion of current practice.

Clinical trials (London, England)·2026
Same author

Study design for an emulated trial of a 2 arm, parallel, stratified, adaptive, RCT of CABG versus PCI in people requiring myocardial revascularization at high risk (High-Risk REVASC).

American heart journal·2026
Same author

Predicting 30-day mortality after hospital admission for heart failure: the National Heart Failure Audit for England and Wales.

Heart (British Cardiac Society)·2026
Same author

A Bayesian framework to evaluate non-inferiority in randomized controlled trials of uncommon conditions.

Journal of clinical epidemiology·2025

Area of Science:

  • Biostatistics
  • Clinical Trials Methodology
  • Epidemiology

Background:

  • Cluster randomized trials often involve complex hierarchical data structures.
  • Simultaneous analysis of multiple outcomes in these designs presents statistical challenges.
  • Existing methods may not fully capture inter-outcome correlations at individual and cluster levels.

Purpose of the Study:

  • To present a flexible Bayesian modeling strategy for analyzing multivariate outcomes in cluster randomized trials.
  • To estimate intervention effects and between-outcome correlations at both individual and cluster levels.
  • To provide a robust framework for handling complex hierarchical data.

Main Methods:

  • Development of a Bayesian hierarchical model for simultaneous analysis of multiple normally distributed outcomes.

Related Experiment Videos

  • Estimation of intervention effects, individual-level, and cluster-level between-outcome correlations.
  • Proposal of novel prior specifications for covariance matrices to ensure symmetry and non-negative definiteness.

    • Main Results:

    • The Bayesian framework offers advantages, including credible intervals for parameter functions and informative priors.
    • Specific solutions are proposed for models with three or four-plus multivariate outcomes.
    • The method was successfully applied to a cluster randomized trial in coronary heart disease prevention.

    Conclusions:

    • The presented Bayesian modeling strategy provides a flexible and powerful tool for analyzing hierarchical multivariate outcomes.
    • This approach enhances the estimation of intervention effects and complex correlation structures.
    • The methodology is broadly applicable to various research areas with similar data structures.