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

Bayesian meta-analysis for longitudinal data models using multivariate mixture priors.

Hedibert Freitas Lopes1, Peter Müller, Gary L Rosner

  • 1Departamento de Métodos Estatísticos, Universidade Federal do Rio de Janeiro, Caixa Postal 68530 - 21945-970, Rio de Janeiro, RJ, Brazil. hedibert@im.ufrj.br

Biometrics
|May 24, 2003
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

The Impact of Baseline Sleep as a Potential Moderator of Weight Loss Intervention in Breast Cancer Survivors: Results From the POWER-Remote Trial.

Obesity (Silver Spring, Md.)·2025
Same author

A Bias-Corrected Bayesian Nonparametric Model for Combining Studies With Varying Quality in Meta-Analysis.

Biometrical journal. Biometrische Zeitschrift·2025
Same author

Stochastic Volatility Models with Skewness Selection.

Entropy (Basel, Switzerland)·2024
Same author

Bayesian Double Feature Allocation for Phenotyping with Electronic Health Records.

Journal of the American Statistical Association·2023
Same author

A comprehensive study of the interactions in the B. subtilis degradosome with special emphasis on the role of the small proteins SR1P and SR7P.

Molecular microbiology·2023
Same author

The small-molecule kinase inhibitor ceritinib, unlike imatinib, causes a significant disturbance of lipid membrane integrity: A combined experimental and MD study.

Chemistry and physics of lipids·2023

This study introduces flexible longitudinal data models with random effects, enhancing analysis of population heterogeneity and enabling meta-analysis across studies. The novel approach models white blood cell counts to assess cancer treatment toxicity.

Area of Science:

  • Biostatistics
  • Longitudinal Data Analysis
  • Statistical Modeling

Background:

  • Current longitudinal models with random effects have limitations in accommodating population heterogeneity and performing meta-analyses.
  • Existing methods struggle with outliers and nonlinear relationships in subject-specific covariate regressions.

Purpose of the Study:

  • To propose a generalized class of longitudinal data models with random effects.
  • To incorporate flexible mixture-of-multivariate-normals for random effects, allowing for population heterogeneity and nonlinearity.
  • To introduce a hierarchical extension for meta-analysis across related studies.

Main Methods:

  • Utilized a flexible mixture of multivariate normals for random-effects distributions.
  • Implemented a hierarchical extension decomposing random effects into common and study-specific measures.

Related Experiment Videos

  • Employed reversible jump posterior simulation for inference, allowing a random number of mixture terms.

    • Main Results:

    • The proposed model effectively accommodates population heterogeneity, outliers, and nonlinear regressions.
    • The hierarchical structure successfully integrates information from multiple related studies.
    • Applied to Cancer and Leukemia Group B (CALGB) studies, modeling white blood cell counts over time.

    Conclusions:

    • The generalized longitudinal models offer enhanced flexibility for analyzing complex population data.
    • The hierarchical framework is valuable for meta-analysis, capturing both common and study-specific variability.
    • The model provides a robust approach for characterizing treatment toxicity through longitudinal measurements.