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

Analysing repeated measurements with possibly missing observations by modelling marginal distributions.

L J Wei1, D O Stram

  • 1Department of Biostatistics, University of Michigan, Ann Arbor 48109.

Statistics in Medicine
|January 1, 1988
PubMed
Summary

This study introduces quasi-likelihood models for analyzing repeated measurements with time-dependent covariates and missing data. The methods provide robust inference on covariate effects across the study period.

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

Nonparametric estimation of the total treatment effect with multiple outcomes in the presence of terminal events.

Biometrics·2026
Same author

Radiation Dose and Solid Cancer Mortality Risk in the Techa River and East Urals Radioactive Trace Cohorts in 1950-2016.

Radiation research·2025
Same author

Progression-free survival as a surrogate endpoint in myeloma clinical trials: an evolving paradigm.

Blood cancer journal·2024
Same author

Advancing Transthyretin Amyloidosis Drug Development in an Evolving Treatment Landscape: Amyloidosis Forum Meeting Proceedings.

Advances in therapy·2024
Same author

[Exploration and contemplation of homogenized education of specialists in pulmonary and critical care medicine at member hospitals of a hospital consortium].

Zhonghua jie he he hu xi za zhi = Zhonghua jiehe he huxi zazhi = Chinese journal of tuberculosis and respiratory diseases·2024
Same author

Robust Alternatives to ANCOVA for Estimating the Treatment Effect via a Randomized Comparative Study.

Journal of the American Statistical Association·2023

Area of Science:

  • Biostatistics
  • Longitudinal Data Analysis
  • Statistical Modeling

Background:

  • Repeatedly observed subjects often present time-dependent covariates and missing data.
  • Analyzing such complex longitudinal data requires flexible statistical frameworks.
  • Existing methods may impose restrictive assumptions on data dependence.

Purpose of the Study:

  • To develop and illustrate quasi-likelihood models for marginal distributions in longitudinal studies.
  • To analyze the effects of time-dependent covariates on response variables over time.
  • To provide inference procedures without assuming parametric dependence structures.

Main Methods:

  • Utilized quasi-likelihood models for marginal distributions at each time point.
  • Employed McCullagh and Nelder's class of models.

Related Experiment Videos

  • Developed methods for large sample inference, including approximate joint normality of regression coefficients.

    • Main Results:

    • Quasi-likelihood estimates of time-specific regression coefficients are approximately jointly normal for large samples.
    • Inference procedures offer a global view of covariate effects throughout the study.
    • A lack-of-fit test was developed to assess model adequacy.

    Conclusions:

    • The proposed quasi-likelihood approach offers a flexible and powerful tool for longitudinal data analysis.
    • The methods are applicable even with time-dependent covariates and missing observations.
    • The study provides practical illustrations with real-life examples.