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

An exact McNemar test for paired binary Markov chains

W Smith1, A R Solow

  • 1Statistics Department, Temple University, Philadelphia, Pennsylvania 19122, USA.

Biometrics
|September 1, 1996
PubMed
Summary

This study introduces an exact test for comparing marginal distributions in bivariate binary Markov chains, extending the McNemar test. The new Markov-McNemar test offers accurate p-values and performs comparably to the classical McNemar test.

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

An application of circular-linear correlation analysis to the relationship between Freon concentration and wind direction in Woods Hole, Massachusetts.

Environmental monitoring and assessment·2013
Same author

Detecting change in the composition of multispecies community.

Biometrics·2009
Same author

Vibrotactile threshold measurement for detecting peripheral neuropathy: defining variability and a normal range for clinical and research use.

Diabetologia·2007
Same author

Angioedema, lymphoproliferative disorder and angiotensin-converting enzyme inhibitors: masking of diagnosis by corticosteroids.

Internal medicine journal·2007
Same author

Vision rehabilitation: recipients' perceived efficacy of rehabilitation.

Ophthalmic epidemiology·2007
Same author

Microcalcifications of the breast: size matters! A mammographic-histologic correlation study.

Pathologica·2007

Area of Science:

  • Statistics
  • Biostatistics
  • Computational Biology

Background:

  • Bivariate binary Markov chains model sequential binary outcomes.
  • Comparing marginal distributions is crucial in various scientific fields.
  • Existing methods may lack exactness for Markov chain data.

Purpose of the Study:

  • To develop an exact statistical test for the equality of limiting marginal distributions in bivariate binary Markov chains.
  • To provide a method for comparing paired binary data in dependent sequences.
  • To evaluate the performance and applicability of the proposed test.

Main Methods:

  • Extension of the McNemar test for paired binary data.
  • Utilizing cell occupancy statistics from the Bose-Einstein model for null distribution.

Related Experiment Videos

  • Computation of exact p-values for one-sided tests.
  • Analysis of the test statistic's mean and variance.

    • Main Results:

    • An exact test, termed the Markov-McNemar test, was derived.
    • The null distribution relies on Bose-Einstein statistics.
    • Exact p-values and test statistic moments were determined.
    • The Markov-McNemar test demonstrated power comparable to the classical McNemar test under independence.

    Conclusions:

    • The Markov-McNemar test provides an exact solution for comparing marginal distributions in bivariate binary Markov chains.
    • The method is applicable to biological sequence comparisons, such as ribosomal DNA.
    • This extends the utility of McNemar-type tests to dependent data structures.