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

Testing proportionality in the proportional odds model fitted with GEE.

T R Stiger1, H X Barnhart, J M Williamson

  • 1Department of Biometrics, Pfizer Inc., Groton, CT 06340, USA. stiget@pfizer.com

Statistics in Medicine
|July 10, 1999
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

State-independent ionic conductivity.

Science (New York, N.Y.)·2025
Same author

Cellulo-Cutaneous Erysipelas.

The Southern medical record·2022
Same author

Use of atorvastatin in systemic lupus erythematosus in children and adolescents.

Arthritis and rheumatism·2011
Same author

Laboratory markers of cardiovascular risk in pediatric SLE: the APPLE baseline cohort.

Lupus·2010
Same author

Some Practical Points in the Treatment of Haemoptysis.

British medical journal·2010
Same author

The Laryngeal Complications of Consumption.

British medical journal·2010

This study introduces new statistical tests for proportional odds models with correlated categorical data. These robust and model-based tests, including score and Wald tests, improve the analysis of medical study data.

Area of Science:

  • Statistics
  • Biostatistics
  • Categorical Data Analysis

Background:

  • Generalized estimating equations (GEE) are widely used for correlated binary data.
  • GEE has been extended for nominal and ordinal categorical data, including proportional odds models.
  • Assessing the proportional odds assumption is crucial for model validity.

Purpose of the Study:

  • To develop and evaluate robust and model-based score and Wald tests for the proportional odds assumption.
  • To compare the performance of these tests in analyzing correlated categorical data.
  • To provide practical tools for medical researchers analyzing complex categorical outcomes.

Main Methods:

  • Utilizing Generalized Estimating Equations (GEE) for fitting proportional odds models.

Related Experiment Videos

  • Developing robust (empirically corrected) and model-based score and Wald tests.
  • Simulating data from various models to evaluate test performance in small to moderate samples.

    • Main Results:

    • The proposed score and Wald tests effectively assess the proportional odds assumption.
    • Both robust and model-based versions demonstrate utility in simulations.
    • The tests were illustrated on three real-world medical study datasets.

    Conclusions:

    • The developed statistical tests offer reliable methods for validating proportional odds models in GEE.
    • These methods enhance the analysis of correlated nominal and ordinal data in medical research.
    • The study provides valuable statistical tools for biostatisticians and researchers.