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

Deviations from the population-averaged versus cluster-specific relationship for clustered binary data.

Thomas R Ten Have1, Sarah J Ratcliffe, Beth A Reboussin

  • 1Department of Biostatistics and Epidemiology, University of Pennsylvania School of Medicine, Blockley Hall, 6th FLR, 423 Guardian Drive, Philadelphia, PA 19104-6021, USA. ttenhave@cceb.upenn.edu

Statistical Methods in Medical Research
|January 30, 2004
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

Are older adult research participants representative of the general population? Results from 19 clinical studies at one academic research center.

Contemporary clinical trials·2026
Same author

Association of resilience with hemoglobin A1c among youth and young adults with youth-onset diabetes.

Annals of epidemiology·2026
Same author

The Impact of Product Packaging on Perceptions of Cannabis Edibles: Results from Two Randomized Experiments.

Substance use & misuse·2026
Same author

Multi-Omic, Multi-Tissue Responses to Acute Exercise in Sedentary Adults: Findings from the Molecular Transducers of Physical Activity Consortium.

bioRxiv : the preprint server for biology·2026
Same author

Machine Learning-Based Stepping Filter Improves Estimates of Moderate-to-Vigorous-Intensity Physical Activity from Wrist Actigraphy.

Digital biomarkers·2026
Same author

Health claims about cannabidiol (CBD) at the point-of-sale in three U.S. states with disparate cannabis policies.

Preventive medicine reports·2026
Same journal

Modeling treatment effects on absorbing outcomes in clinical trials: Leveraging longitudinal and ordinal data for efficiency gains.

Statistical methods in medical research·2026
Same journal

A joint model for a longitudinal outcome and a progressive multistate model under a mixed observation scheme.

Statistical methods in medical research·2026
Same journal

Efficient semi-supervised estimation of optimal individualized treatment regimes with survival outcome.

Statistical methods in medical research·2026
Same journal

Asymptotic online FWER control for dependent test statistics.

Statistical methods in medical research·2026
Same journal

Regression analysis of misclassified current status data with potentially unknown test accuracy.

Statistical methods in medical research·2026
Same journal

Bayesian multivariate linear mixed-effects models with varied association structures.

Statistical methods in medical research·2026
See all related articles

Comparing mixed-effects and population-averaged logistic models reveals assumption violations. Analyzing their relationship serves as sensitivity analysis for clustered binary data, particularly longitudinal outcomes.

Area of Science:

  • Biostatistics
  • Statistical Modeling
  • Longitudinal Data Analysis

Background:

  • Mixed-effects and population-averaged logistic models are debated for clustered binary data.
  • Investigating their relationship offers a sensitivity analysis for model assumptions.

Purpose of the Study:

  • To explore the relationship between mixed-effects and population-averaged logistic models.
  • To identify assumption violations in these models for clustered binary and longitudinal data.

Main Methods:

  • Utilized several datasets to demonstrate departures from theoretical relationships between models.
  • Modified random intercept logistic models to address negative intra-cluster correlations, cluster confounding, and baseline effect confounding.
  • Compared modified models with Generalized Estimating Equations (GEE) and conditional likelihood estimation.

Related Experiment Videos

Main Results:

  • Violations like negative intra-cluster correlations and confounding alter the expected odds ratio relationship.
  • Naive random intercept logistic models showed bias under these violations.
  • Modified models successfully accommodated assumption violations.

Conclusions:

  • The relationship between mixed-effects and population-averaged models is a valuable sensitivity analysis tool.
  • Standard models require modification to handle specific assumption violations in clustered binary data.
  • Correcting for these violations is crucial for accurate analysis of longitudinal binary outcomes.