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

Overcoming ecologic bias using the two-phase study design.

Jon Wakefield1, Sebastien J-P A Haneuse

  • 1Department of Statistics, University of Washington, Seattle, WA 98195-7232, USA. jonno@u.washington.edu

American Journal of Epidemiology
|February 14, 2008
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

Global Sensitivity Analysis for Studies Extending Inferences From a Randomized Trial to a Target Population.

Statistics in medicine·2026
Same author

Excess Mortality Estimation.

Annual review of statistics and its application·2026
Same author

Direct-Assisted Bayesian Unit-level Modeling for Small Area Estimation of Rare Event Prevalence.

Journal of survey statistics and methodology·2026
Same author

Toward a Principled Workflow for Prevalence Mapping Using Household Survey Data.

Journal of survey statistics and methodology·2026
Same author

Small Area Estimation of Education Levels in Low- and Middle-Income Countries.

The annals of applied statistics·2026
Same author

BARTSIMP: Flexible spatial covariate modeling and prediction using Bayesian Additive Regression Trees.

Spatial and spatio-temporal epidemiology·2025
Same journal

A SIMPLE AND POWERFUL TEST OF VACCINE WANING.

American journal of epidemiology·2026
Same journal

Association Between maternal body mass index, offspring growth and pubertal timing: results from a longitudinal birth cohort study.

American journal of epidemiology·2026
Same journal

Correction to: Developing a novel algorithm to identify incident and prevalent dementia in Medicare claims-the ARIC Study.

American journal of epidemiology·2026
Same journal

RE: advancing observational research on arts and health: theory-informed approaches using the RADIANCE framework.

American journal of epidemiology·2026
Same journal

Maternal Cesarean Section and Offspring ASD or ADHD Risk: A Nurses' Health Study II Analysis.

American journal of epidemiology·2026
Same journal

Immigration and epigenetic age acceleration in the health and retirement study: differences Between Hispanics and Non-Hispanics.

American journal of epidemiology·2026
See all related articles

This study introduces a two-phase study design to overcome ecologic bias in epidemiologic research. This method effectively combines aggregate and individual data to provide more accurate exposure assessments.

Area of Science:

  • Epidemiology
  • Biostatistics
  • Public Health Research

Background:

  • Ecologic (aggregate) data are common in epidemiology but suffer from ecologic bias due to inability to assess within-group variability.
  • Ecologic bias arises when aggregate data cannot capture individual-level variations in exposures and confounders.
  • Addressing ecologic bias requires integrating individual-level data with aggregate data.

Purpose of the Study:

  • To present and illustrate the two-phase study design as a framework for removing ecologic bias.
  • To demonstrate how combining aggregate and individual data can improve epidemiologic research.
  • To estimate the association between infant mortality and birth weight while controlling for ecologic bias.

Main Methods:

  • A two-phase study design is proposed: Phase 1 uses aggregate data for stratification, and Phase 2 samples individual data within strata.

Related Experiment Videos

  • Phase 1 stratifies outcomes by area, confounders, and discretized exposures.
  • Phase 2 collects accurate individual-level exposure and confounder data within strata.

    • Main Results:

    • The two-phase design effectively removes ecologic bias by characterizing within-area exposure variability.
    • The study demonstrated improved efficiency compared to using case-control data alone.
    • An example estimating the association between infant mortality and birth weight in North Carolina (2000-2004) is presented, controlling for gender and race.

    Conclusions:

    • The two-phase study design is an effective framework for controlling ecologic bias in epidemiologic studies.
    • This approach enhances statistical power and efficiency by integrating aggregate and individual data.
    • The method offers advantages for accurately assessing exposure-disease relationships in population health research.