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 comparison of methods for calculating a stratified kappa.

W Barlow1, M Y Lai, S P Azen

  • 1Center for Health Studies, Group Health Cooperative, Seattle, WA 98101-1448.

Statistics in Medicine
|September 1, 1991
PubMed
Summary

This study introduces stratified kappa to measure interrater agreement when confounders are present. Weighting by sample size proved most efficient for assessing agreement across different disease severities.

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

Taenia saginata Infection in a 25-Year-Old Immigrant in Malaysia: A Case Study.

Tropical biomedicine·2026
Same author

High incidence of Plasmodium knowlesi malaria compared to other human malaria species in several hospitals in Malaysia.

Tropical biomedicine·2021
Same author

Experimental Study on Plasmodium knowlesi Normocyte Binding Protein Xa Region II (PkNBPXaII) for Erythrocyte Binding.

Tropical biomedicine·2021
Same author

Enteral myiasis causing acute dysentery: A case report.

Tropical biomedicine·2021
Same author

Elimination of contamination in loop-mediated isothermal amplification assay for detection of human malaria.

Tropical biomedicine·2021
Same author

Visual function assessment in simulated real-life situations in patients with age-related macular degeneration compared to normal subjects.

Eye (London, England)·2014

Area of Science:

  • Statistics
  • Biostatistics
  • Medical Informatics

Background:

  • The kappa coefficient is used to measure interrater agreement in nominal categories.
  • Confounding variables can affect the marginal probability of classification, impacting agreement assessment.
  • Existing methods may not adequately account for subject grouping based on confounders.

Purpose of the Study:

  • To develop and evaluate a stratified kappa index for assessing interrater agreement in the presence of confounding variables.
  • To compare different weighting schemes for calculating stratified kappa.
  • To assess the efficiency of various weighting methods under different conditions.

Main Methods:

  • A stratified kappa index was developed using weighted summations of individual kappas.

Related Experiment Videos

  • Three weighting schemes were investigated: equal weighting, weighting by table size, and weighting by inverse variance.
  • A simulation study compared these methods across varying probability structures and sample sizes.

    • Main Results:

    • Weighting by sample size demonstrated moderate efficiency across most simulated conditions.
    • The stratified kappa approach effectively accounts for confounding variables in agreement assessment.
    • The study illustrates application in assessing surgeon and grader agreement on retinal characteristics, stratified by disease severity.

    Conclusions:

    • Stratified kappa provides a robust method for measuring interrater agreement when confounders are present.
    • Weighting by sample size is a recommended approach for calculating stratified kappa.
    • This method enhances the reliability of observer agreement studies in clinical settings.