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

A method for imputing missing data in longitudinal studies.

Ada O Youk1, Roslyn A Stone, Gary M Marsh

  • 1Department of Biostatistics, Graduate School of Public Health, University of Pittsburgh, Pittsburgh, PA 15261, USA. ayouk@pitt.edu

Annals of Epidemiology
|June 5, 2004
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

Historical Study of Workers Exposed to Styrene in the US Reinforced Plastics and Composite Industry: Findings From a 2019 Mortality Update.

Journal of occupational and environmental medicine·2025
Same author

Severe asthma exacerbations associated with unconventional natural gas development activity in area of concentrated development.

The Journal of asthma : official journal of the Association for the Care of Asthma·2025
Same author

Impact of a community-based lifestyle intervention with initial sedentary reduction or physical activity increasing goals on self-reported health-related quality of life.

Translational behavioral medicine·2025
Same author

Implementing brief behavioral treatment for insomnia in Department of Veterans Affairs Primary Care Mental Health Integration clinics: Reach outcomes from a hybrid type 3 effectiveness-implementation trial.

Psychological services·2025
Same author

Outcomes of Women Undergoing Noncardiac Surgery in Veterans Affairs Compared With Non-Veterans Affairs Care Settings.

JAMA surgery·2024
Same author

A Retrospective Cohort Study to Evaluate Adding Biomarkers to the Risk Analysis Index of Frailty.

The Journal of surgical research·2023
Same journal

GLP-1 receptor agonist medications for weight loss: Sociodemographic patterns of awareness, use, and access in a U.S. national cohort.

Annals of epidemiology·2026
Same journal

Even low levels of physical activity are associated with lower all-cause mortality: A cohort study of 594,000 US adults.

Annals of epidemiology·2026
Same journal

Comment on "Distinct differences between COVID-19 vaccine refusers and vaccine hesitant in the United States: Results from a population-based survey and latent class analysis".

Annals of epidemiology·2026
Same journal

Translating caregiver-identified neighborhood features into quantitative variables for statistical analyses of effects on child health.

Annals of epidemiology·2026
Same journal

Associations between the built environment and body mass index among a residentially stable cohort of mid-older aged adults in Brisbane, Australia (2007-2016).

Annals of epidemiology·2026
Same journal

Unmeasured air pollution, adiposity measurement, and life-stage transitions in the HABITAT built environment-BMI analysis.

Annals of epidemiology·2026
See all related articles

This study introduces an Iterative Allocation Algorithm (IAA) to accurately estimate race-specific person-years in cohort studies with missing racial data. The IAA offers reliable denominators for calculating mortality rates and Standardized Mortality Ratios (SMRs).

Area of Science:

  • Epidemiology
  • Biostatistics
  • Occupational Health

Background:

  • Cohort studies often face challenges with missing demographic data, particularly race.
  • Accurate person-year denominators are crucial for calculating incidence rates and Standardized Mortality Ratios (SMRs).
  • Imputation methods are needed to address incomplete covariate information in epidemiological research.

Purpose of the Study:

  • To develop and evaluate a model-based Iterative Allocation Algorithm (IAA) for imputing race-specific person-years.
  • To address the issue of unknown racial data in cohort studies.
  • To compare the IAA with the Proportional Allocation Method (PAM).

Main Methods:

  • Adapted an Expectation-Maximization (EM) algorithm for censored data regression.

Related Experiment Videos

  • Estimated the probability of a person being white to impute race-specific person-years.
  • Utilized the bootstrap method for variance estimation.
  • Compared IAA with the Proportional Allocation Method (PAM).

    • Main Results:

    • The IAA estimated age-time-race-specific person-years with approximately 20% relative variation in a cohort with 41% missing racial data.
    • Deaths were estimated less reliably than person-years.
    • Standardized Mortality Ratios (SMRs) from IAA and PAM were more similar for non-white workers than for white workers.

    Conclusions:

    • The Iterative Allocation Algorithm (IAA) reliably estimates race-specific person-year denominators in cohort studies with missing racial data.
    • The IAA is applicable to other incompletely observed categorical covariates.
    • This method allows for computation and modeling of internal cohort rates or SMRs with bootstrap confidence intervals accounting for racial data uncertainty.