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

Interval estimation of the kappa coefficient with binary classification and an equal marginal probability model.

J M Nam1

  • 1Biostatistics Branch, National Cancer Institute, Rockville, Maryland 20892-7368, USA. namj@mail.nih.gov

Biometrics
|July 6, 2000
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

A pilot study to rate determinants of exposure from videotaped work activities of farmers' use of pesticides.

Applied occupational and environmental hygiene·2001
Same author

Power and sample size for testing homogeneity of relative risks in prospective studies.

Biometrics·2001
Same author

Association of major histocompatibility complex determinants with the development of symptomatic and asymptomatic genital herpes simplex virus type 2 infections.

The Journal of infectious diseases·1999
Same author

Human leukocyte antigen class II alleles associated with human T-cell lymphotropic virus type I infection and adult T-cell leukemia/lymphoma in a Black population.

Journal of the National Cancer Institute·1998
Same author

Power and sample size for stratified prospective studies using the score method for testing relative risk.

Biometrics·1998
Same author

Establishing equivalence of two treatments and sample size requirements in matched-pairs design.

Biometrics·1998

A new likelihood score method provides accurate interval estimation for the intraclass kappa coefficient of agreement in binary classification. This method outperforms crude intervals and offers shorter lengths than chi-square procedures in specific scenarios.

Area of Science:

  • Biostatistics
  • Statistical Methods

Background:

  • Assessing inter-rater reliability is crucial in binary classification tasks.
  • Existing methods for interval estimation of the intraclass kappa coefficient have limitations.

Purpose of the Study:

  • To derive and evaluate a likelihood score method for interval estimation of the intraclass kappa coefficient.
  • To compare the statistical properties of the score method with existing chi-square and crude confidence interval methods.

Main Methods:

  • Derivation of a likelihood score method based on Bartlett's general theory.
  • Exact evaluation of statistical properties, including coverage percentages and interval lengths.
  • Comparison across small and medium sample sizes.

Main Results:

Related Experiment Videos

  • The likelihood score method and the chi-square method demonstrate satisfactory coverage percentages.
  • The crude confidence interval method shows unsatisfactory coverage.
  • The score method yields shorter expected interval lengths than the chi-square procedure under very low or very high response rates.

Conclusions:

  • The likelihood score method is a reliable and efficient approach for interval estimation of the intraclass kappa coefficient.
  • It offers advantages over crude methods and competitive performance against chi-square methods, particularly in specific response rate conditions.