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

Large hierarchical Bayesian analysis of multivariate survival data

P Gustafson1

  • 1Department of Statistics, University of British Columbia, Vancouver, Canada.

Biometrics
|March 1, 1997
PubMed
Summary

This study introduces Bayesian hierarchical models for analyzing grouped failure times in clinical trials. It avoids parametric assumptions for survival data by using Cox partial likelihood, enhancing statistical reliability.

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

Analysis of negligence claims after carotid artery interventions over 20 years in Sweden.

Scandinavian journal of surgery : SJS : official organ for the Finnish Surgical Society and the Scandinavian Surgical Society·2025
Same author

Maternal and pregnancy predictive risk factors for having a compensated maternal injury claim: a Swedish nationwide cohort study.

Scientific reports·2023
Same author

The role of prolactin in the suppression of Crh mRNA expression during pregnancy and lactation in the mouse.

Journal of neuroendocrinology·2017
Same author

Role of primary T-cell immunodeficiency and hepatitis B coinfection on spontaneous clearance of hepatitis C: The BC Hepatitis Testers Cohort.

Journal of viral hepatitis·2016
Same author

Disconnected by design: analytic approach in treatment networks having no common comparator.

Research synthesis methods·2016
Same author

Beta-interferon exposure and onset of secondary progressive multiple sclerosis.

European journal of neurology·2015

Area of Science:

  • Statistics
  • Biostatistics
  • Survival Analysis

Background:

  • Grouped failure time data is common in statistical practice, especially with multiple responses per unit (e.g., patients, centers).
  • Traditional methods may rely on questionable parametric assumptions for survival data.
  • Bayesian hierarchical models offer a flexible framework for such complex data structures.

Purpose of the Study:

  • To present a Bayesian hierarchical modeling approach for analyzing grouped failure times.
  • To avoid making strong parametric assumptions at the initial stage of survival time modeling.
  • To provide a robust statistical framework for complex observational data.

Main Methods:

  • Utilizes Cox partial likelihood for modeling survival times at the first stage, avoiding parametric assumptions.

Related Experiment Videos

  • Employs parametric modeling for unit-specific parameters at subsequent stages.
  • Employs Markov chain Monte Carlo (MCMC) methods, specifically hybrid Monte Carlo, for posterior distribution examination.

    • Main Results:

    • The proposed method effectively models grouped failure times without compromising initial survival data integrity.
    • Parametric assumptions are confined to later stages, where they are considered more acceptable.
    • Markov chain Monte Carlo methods enable efficient exploration of the posterior distribution.

    Conclusions:

    • Bayesian hierarchical models provide a suitable framework for analyzing grouped failure times.
    • The combination of Cox partial likelihood and MCMC offers a robust and flexible approach.
    • This methodology enhances the reliability of statistical analyses in complex settings like clinical trials.