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

Dependence estimation for marginal models of multivariate survival data

M R Segal1, J M Neuhaus, I R James

  • 1Division of Biostatistics, University of California, San Francisco 94143-0560, USA. mark@biostat.ucsf.edu

Lifetime Data Analysis
|January 1, 1997
PubMed
Summary

This study addresses challenges in estimating dependence for multivariate survival data, proposing a novel approach to improve regression coefficient accuracy. The new method, based on design effects, offers a practical solution for complex survival analyses.

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

Unsupervised Online Paired Associates Learning Task from the Cambridge Neuropsychological Test Automated Battery (CANTAB®) in the Brain Health Registry.

The journal of prevention of Alzheimer's disease·2024
Same author

Machine intelligence identifies soluble TNFa as a therapeutic target for spinal cord injury.

Scientific reports·2021
Same author

Interplay of strain and race/ethnicity in the innate immune response to M. tuberculosis.

PloS one·2018
Same author

Biomarkers of Tuberculosis Severity and Treatment Effect: A Directed Screen of 70 Host Markers in a Randomized Clinical Trial.

EBioMedicine·2017
Same author

Serum biomarkers of treatment response within a randomized clinical trial for pulmonary tuberculosis.

Tuberculosis (Edinburgh, Scotland)·2015
Same author

RAD51 loss of function abolishes gene targeting and de-represses illegitimate integration in the moss Physcomitrella patens.

DNA repair·2010

Area of Science:

  • Biostatistics
  • Survival Analysis
  • Statistical Modeling

Background:

  • Existing methods for multivariate survival data offer regression coefficients and variance estimates.
  • Parametric and semiparametric models exist, providing robust variances for regression parameters.
  • However, these methods have not adequately addressed the estimation of dependence.

Purpose of the Study:

  • To investigate the limitations of current generalized estimating equations (GEE) approaches for dependence estimation in multivariate survival data.
  • To propose and evaluate an alternative method for dependence estimation.
  • To assess the impact of dependence estimation issues on regression coefficient estimation.

Main Methods:

  • Review and critique of generalized estimating equations (GEE) for multivariate survival data.

Related Experiment Videos

  • Development of an alternative, ad hoc approach for dependence estimation using design effects.
  • Evaluation of the proposed method through simulation studies and illustrative examples.

    • Main Results:

    • Generalized estimating equations (GEE) exhibit problems when applied to multivariate survival data, potentially affecting regression coefficient estimates.
    • The proposed ad hoc method based on design effects provides a viable alternative for dependence estimation.
    • Simulations and examples demonstrate the utility of the new approach.

    Conclusions:

    • Current GEE methods are insufficient for accurate dependence estimation in multivariate survival analysis.
    • The proposed design effect-based method offers an improved approach to dependence estimation.
    • Accurate dependence estimation is crucial for reliable regression coefficient estimation in complex survival data.