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

Exact unconditional tests for a 2 x 2 matched-pairs design.

R L Berger1, K Sidik

  • 1Statistics Department, North Carolina State University, Raleigh, NC 27695-8203, USA. rberger@nsf.gov

Statistical Methods in Medical Research
|April 1, 2003
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

Achievement of Target Gain Larger than Unity in an Inertial Fusion Experiment.

Physical review letters·2024
Same author

Alpha heating of indirect-drive layered implosions on the National Ignition Facility.

Physical review. E·2023
Same author

Hotspot parameter scaling with velocity and yield for high-adiabat layered implosions at the National Ignition Facility.

Physical review. E·2020
Same author

High-Performance Indirect-Drive Cryogenic Implosions at High Adiabat on the National Ignition Facility.

Physical review letters·2018
Same author

Collisional damping rates for electron plasma waves reassessed.

Physical review. E·2018
Same author

Longitudinal and Transverse Instability of Ion Acoustic Waves.

Physical review letters·2017
Same journal

A joint model for a longitudinal outcome and a progressive multistate model under a mixed observation scheme.

Statistical methods in medical research·2026
Same journal

Efficient semi-supervised estimation of optimal individualized treatment regimes with survival outcome.

Statistical methods in medical research·2026
Same journal

Asymptotic online FWER control for dependent test statistics.

Statistical methods in medical research·2026
Same journal

Regression analysis of misclassified current status data with potentially unknown test accuracy.

Statistical methods in medical research·2026
Same journal

Bayesian multivariate linear mixed-effects models with varied association structures.

Statistical methods in medical research·2026
Same journal

Inference about the ratio of age-standardized rates between two overlapping populations.

Statistical methods in medical research·2026
See all related articles

This study introduces four exact unconditional tests for comparing two proportions in matched-pairs binary data. The best-performing test utilizes McNemar's statistic with a confidence interval p-value for accurate and powerful hypothesis testing.

Area of Science:

  • Biostatistics
  • Statistical Inference
  • Clinical Trial Design

Background:

  • Comparing paired binary outcomes is crucial in medical research.
  • Existing methods like McNemar's test have limitations in size and power.
  • Nuisance parameters complicate exact hypothesis testing in 2x2 matched-pairs designs.

Purpose of the Study:

  • To develop and evaluate novel exact unconditional tests for comparing two proportions in binary matched-pairs data.
  • To assess the performance (size and power) of proposed tests against existing methods.
  • To identify the most accurate and powerful statistical test for this specific design.

Main Methods:

  • Development of four exact unconditional tests utilizing the monotonicity of the multinomial distribution.

Related Experiment Videos

  • Reduction of nuisance parameter dimensionality for computational efficiency.
  • Comparison of proposed tests with the exact conditional binomial test and asymptotic McNemar's test.
  • Evaluation of test size and power through simulations or theoretical analysis.

    • Main Results:

    • Tests based on confidence interval p-values demonstrate superior power compared to standard p-value tests.
    • The exact conditional binomial test is found to be conservative and lacks power.
    • Asymptotic McNemar's test exhibits an inflated Type I error rate (incorrect size).
    • The test combining McNemar's statistic with a confidence interval p-value is the most powerful and maintains correct size.

    Conclusions:

    • Exact unconditional tests offer improved performance for comparing paired binary proportions.
    • Confidence interval-based p-values enhance the power of hypothesis tests.
    • The proposed McNemar's statistic with confidence interval p-value test is recommended for its accuracy and power in 2x2 matched-pairs analyses.