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

Analysis of repeated measures data with clumping at zero.

Janet A Tooze1, Gary K Grunwald, Richard H Jones

  • 1National Cancer Institute, Executive Plaza North, Suite 3131, 6130 Executive Blvd, MSC7354, Bethesda, MD 20892-7354, USA. toozej@mail.nih.gov

Statistical Methods in Medical Research
|August 29, 2002
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

Obesity and Age Elevate Tissue-Resident Microbiota Akkermansia muciniphila to Induce Oxidative Stress and Promote Breast Cancer Risk.

Cancer research·2026
Same author

How Is U.S. Food-Insecurity Related to Dietary Quality? A Scoping Review to Inform Nutrition Security Across the Lifespan.

Nutrients·2026
Same author

Leveraging questionnaire-based physical activity levels (PAL) and the Goldberg method to evaluate the biological plausibility of self-reported energy intake: A doubly labeled water validation study.

American journal of epidemiology·2026
Same author

Application of the Total Nutrient Index as a Precision Nutrition Tool to Address Dietary Recommendations Across the Life Course.

Journal of the Academy of Nutrition and Dietetics·2026
Same author

Dietary Pattern-Induced Gut Microbiota Differences Are Associated with White Matter Volume Changes in Middle-Aged Female Macaques.

Nutrients·2026
Same author

Corrigendum to 'Optimization of a digital health intervention to enhance well-being among adolescent and young adult cancer survivors: Design and methods of the EMPOWER full factorial trial' [Contemporary Clinical Trials, Vol. 149 (2025) 107783].

Contemporary clinical trials·2026

This study introduces a novel mixed-effects model to analyze correlated, zero-inflated data common in health and biometrics. The model effectively handles non-normality and quantifies covariate effects on zero probabilities and nonzero means.

Area of Science:

  • Biometrics
  • Epidemiology
  • Health Policy Research

Background:

  • Longitudinal data with zero-clumping presents statistical challenges due to correlation and non-normality.
  • Common in biometrics, epidemiology, and health policy, these datasets require specialized modeling approaches.

Purpose of the Study:

  • To present a mixed-effects mixed-distribution model for analyzing repeated measures data with clumping at zero.
  • To allow for correlation between the probability of a nonzero value and the mean of nonzero values.
  • To provide methods for assessing covariate effects on different aspects of the data distribution.

Main Methods:

  • A mixed-effects mixed-distribution model with correlated random effects was developed.
  • The model incorporates separate components for the probability of a nonzero value and the mean of nonzero values.

Related Experiment Videos

  • Random effects accommodate repeated measurements and correlations within subjects.

    • Main Results:

    • The proposed model effectively handles the non-normality and correlation inherent in zero-inflated longitudinal data.
    • Methods were demonstrated for quantifying the impact of predictor variables on zero probability and nonzero means.
    • The model's utility was shown in analyzing medical expenditures using Medical Expenditure Panel Survey data.

    Conclusions:

    • The developed model provides a robust framework for analyzing complex longitudinal data with zero-inflation.
    • It offers interpretable results regarding covariate effects on both the occurrence and magnitude of nonzero outcomes.
    • This approach is applicable to various biostatistical and health services research applications.