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

Modeling repeated count data subject to informative dropout.

P S Albert1, D A Follmann

  • 1Biometric Research Branch, National Cancer Institute, Bethesda, Maryland 20892-7438, USA. albertp@ctep.nci.nih.gov

Biometrics
|September 14, 2000
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

Cancer mortality and geographic inequalities: a detailed descriptive and spatial analysis of social determinants across US counties, 2018-2021.

Public health·2024
Same author

Estimating gestational age at birth from fundal height and additional anthropometrics: a prospective cohort study.

BJOG : an international journal of obstetrics and gynaecology·2018
Same author

Comparison of methods for identifying small-for-gestational-age infants at risk of perinatal mortality among obese mothers: a hospital-based cohort study.

BJOG : an international journal of obstetrics and gynaecology·2016
Same author

Differences in risk factors for incident and recurrent small-for-gestational-age birthweight: a hospital-based cohort study.

BJOG : an international journal of obstetrics and gynaecology·2014
Same author

Estimation of gene-environment interaction by pooling biospecimens.

Statistics in medicine·2012
Same author

Adiposity and sex hormones across the menstrual cycle: the BioCycle Study.

International journal of obesity (2005)·2012
Same journal

Fast penalized generalized estimating equations for large longitudinal functional datasets.

Biometrics·2026
Same journal

Causally-interpretable random-effects meta-analysis.

Biometrics·2026
Same journal

Statistical inference for mean function of partially observed functional time series.

Biometrics·2026
Same journal

Subgroup identification via Interaction Tree and Mixed Model for Repeated Measures with application to Alzheimer's disease.

Biometrics·2026
Same journal

Finite mixtures of linear quantile regressions with concomitant variables: a solution to endogeneity in longitudinal data modeling.

Biometrics·2026
Same journal

Discussion on "INTACT: a method for integration of longitudinal physical activity data from multiple sources" by Jingru Zhang, Erjia Cui, Hongzhe Li, and Haochang Shou.

Biometrics·2026
See all related articles

This study introduces new statistical methods to accurately analyze patient event counts in clinical trials, especially when patient dropout (censoring) is linked to disease severity. These methods improve treatment effect estimates in epilepsy and similar diseases.

Area of Science:

  • Biostatistics
  • Clinical Trials Methodology
  • Epidemiology

Background:

  • Patient outcomes in diseases like epilepsy are often measured by event counts (e.g., seizures).
  • Clinical trial follow-up can be affected by informative censoring, where patient dropout is related to disease severity, potentially biasing results.
  • Existing statistical methods may not adequately account for informative censoring in count data.

Purpose of the Study:

  • To develop and evaluate statistical approaches for analyzing repeated event count data in the presence of informative censoring.
  • To extend the shared random effects model to jointly model count and censoring processes.
  • To provide robust methods for estimating treatment effects in clinical trials with potential bias from informative dropout.

Main Methods:

Related Experiment Videos

  • Developed three statistical strategies: a joint likelihood model with shared random effects, a likelihood model conditioning on dropout times, and a generalized estimating equations (GEE) approach also conditioning on dropout times.
  • Incorporated shared random effects to model dependence between count and censoring processes.
  • Applied and compared these methods using data from an epilepsy clinical trial and through simulation studies.

Main Results:

  • The likelihood-based conditional model demonstrated flexibility in analyzing epilepsy trial data.
  • The developed methods provide more reliable estimates of treatment effects compared to approaches that ignore informative censoring.
  • Simulation studies confirmed the performance of the proposed strategies under various censoring scenarios.

Conclusions:

  • The proposed statistical models effectively address informative censoring in repeated event count data.
  • The likelihood-based conditional approach is particularly well-suited for analyzing data from epilepsy clinical trials.
  • These methods enhance the accuracy and reliability of treatment effect estimations in clinical research for diseases with event counts and potential dropout bias.