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

Regression analysis of correlated binary outcomes.

C F Sheu1

  • 1Department of Psychology, DePaul University, Chicago, IL 60614-3522, USA. csheu@depaul.edu

Behavior Research Methods, Instruments, & Computers : a Journal of the Psychonomic Society, Inc
|June 30, 2000
PubMed
Summary

This study introduces generalized estimating equations (GEE), a regression method for analyzing correlated binary data. GEE correctly adjusts for repeated observations, preventing invalid inferences in statistical analysis.

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

Meta-analysis using linear mixed models.

Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc·2001
Same author

A nonlinear regression approach to estimating signal detection models for rating data.

Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc·2001
Same author

The application of Fourier deconvolution to reaction time data: a cautionary note.

Psychological bulletin·1995
Same author

Causal inferences as perceptual judgements.

Memory & cognition·1995
Same author

Testing global memory models using ROC curves.

Psychological review·1992

Area of Science:

  • Biostatistics
  • Epidemiology
  • Regression Analysis

Background:

  • Analyzing correlated binary outcomes is crucial in various research fields.
  • Ignoring correlations in repeated measures can lead to inaccurate statistical inferences.
  • Existing methods may not adequately address the complexities of dependent binary data.

Purpose of the Study:

  • To describe and illustrate a regression approach for analyzing correlated binary outcomes.
  • To introduce the generalized estimating equations (GEE) method.
  • To demonstrate the utility of GEE in handling repeated binary observations.

Main Methods:

  • The paper presents a nontechnical introduction to the generalized estimating equations (GEE) approach.
  • GEE extends logistic regression to accommodate repeated observations within individuals.
  • A fictitious example is used to illustrate the methodology.

Main Results:

  • GEE regression correctly adjusts for correlations between repeated binary observations.
  • The method provides valid inferences when analyzing clustered or longitudinal binary data.
  • The approach was successfully applied to analyze safer sex practices.

Conclusions:

  • Generalized Estimating Equations (GEE) offer a robust method for analyzing correlated binary data.
  • This approach is essential for accurate statistical inference in studies with repeated measures.
  • The GEE method is applicable to diverse research areas, including public health interventions.

Related Experiment Videos