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

Mixed effects models with bivariate and univariate association parameters for longitudinal bivariate binary response

T R Ten Have1, A Morabia

  • 1Department of Biostatistics and Clinical Epidemiology, The University of Pennsylvania College of Medicine, Philadelphia 19104-6021, USA. ttenhave@cceb.upenn.edu

Biometrics
|April 25, 2001
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

Atomoxetine for depression and other neuropsychiatric symptoms in Parkinson disease.

Neurology·2010
Same author

Undocumented migrants in Switzerland: geographical origin versus legal status as risk factor for tuberculosis.

Journal of immigrant and minority health·2009
Same author

Epidemic and population patterns in the Chinese Empire (243 B.C.E. to 1911 C.E.): quantitative analysis of a unique but neglected epidemic catalogue.

Epidemiology and infection·2009
Same author

The James Lind Library: explaining and illustrating the evolution of fair tests of medical treatments.

The journal of the Royal College of Physicians of Edinburgh·2009
Same author

Twelve-year trends and correlates of dietary salt intakes for the general adult population of Geneva, Switzerland.

European journal of clinical nutrition·2007
Same author

[Determinants of hypercholesterolemia in Geneva: should the focus be on genes or environment?].

Revue medicale suisse·2005

This study introduces a new statistical model to analyze how two health conditions, like hypertension and hypercholesterolemia, change together over time in individuals. The model effectively handles missing data and shows how these conditions are linked longitudinally.

Area of Science:

  • Biostatistics
  • Longitudinal Data Analysis
  • Clinical Trials

Background:

  • Analyzing paired binary outcomes over time requires sophisticated statistical methods.
  • Existing models may not adequately capture dynamic bivariate associations and marginal risks.
  • Longitudinal studies often face challenges with missing data.

Purpose of the Study:

  • To extend marginal models for bivariate binary responses to incorporate random effects.
  • To model changes in bivariate associations and marginal risks over time.
  • To address missing at random (MAR) data in longitudinal studies.

Main Methods:

  • Proposed a marginal model with bivariate log odds ratio and univariate logit components.
  • Included separate normal random effects for bivariate associations and univariate risks.

Related Experiment Videos

  • Assumed conditional independence given random effects to handle missing data.
  • Applied the model to a cardiovascular educational program trial.

    • Main Results:

    • The proposed model successfully captures evolving bivariate associations and marginal risks.
    • Demonstrated feasibility in analyzing longitudinal data with missing values.
    • Outperformed naive bivariate and univariate mixed-effects models in specific contexts.

    Conclusions:

    • The developed random-effects marginal model provides a robust framework for analyzing longitudinal bivariate binary data.
    • This approach enhances understanding of dynamic relationships between health outcomes over time.
    • The model is particularly useful for clinical trial data with complex longitudinal structures.