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

Bayesian tests of extra-Binomial variability.

Chuhsing Kate Hsiao1, Mei-hsien Lee, Robert E Kass

  • 1Division of Biostatistics, Institute of Epidemiology, College of Public Health, National Taiwan University, Taipei 100, Taiwan, ROC.

Statistics in Medicine
|October 30, 2004
PubMed
Summary

This study introduces a Bayesian test to address extra-Binomial variability using approximate Bayes factors. The new method is more powerful than traditional tests and applicable to real-world data.

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

Age, sex, and regional disparities in vision impairment burden among the population with diabetes: a 10-year trend analysis in Taiwan.

Eye (London, England)·2026
Same author

Relative timing and coupling of neural population bursts in large-scale recordings from multiple neuron populations.

Frontiers in computational neuroscience·2026
Same author

Cross-population amplitude coupling in high-dimensional oscillatory neural time series.

Frontiers in computational neuroscience·2026
Same author

A Population Coupling Model Identifies Reduced Propagation from V1 to Higher Visual Areas During Locomotion.

bioRxiv : the preprint server for biology·2026
Same author

SMART-assisted discovery of scalaranes from the marine sponge Lendenfeldia sp. and its anti-osteoclastogenesis activity.

Phytochemistry·2025
Same author

Sclerohumins G-L: Selective cytotoxic diterpenoids featuring a 4/9-fused ring system from the soft coral Sclerophytum humesi.

Phytochemistry·2025

Area of Science:

  • Statistics
  • Biostatistics
  • Computational Statistics

Background:

  • Extra-Binomial variability requires specialized statistical models beyond the standard Binomial distribution.
  • Testing against the Beta-Binomial alternative is complicated by the Binomial distribution's boundary position.
  • Existing asymptotic arguments need modification for these boundary cases.

Purpose of the Study:

  • To propose a novel Bayesian test for extra-Binomial variability.
  • To develop approximate Bayes factors that are computationally efficient.
  • To compare the power of the proposed Bayesian test against the likelihood ratio test.

Main Methods:

  • Development of a Bayesian test utilizing a pair of approximate Bayes factors.
  • Calculation of Bayes factors for scenarios with zero and positive maximum likelihood estimates (MLE) of extra-Binomial variability.

Related Experiment Videos

  • Evaluation of operating characteristics and comparison with the likelihood ratio test.

    • Main Results:

    • The proposed approximate Bayes factors are easy to compute.
    • The Bayesian test demonstrates greater power compared to the likelihood ratio test.
    • Application to three datasets, including logistic regression with a random intercept, shows close agreement with exact Bayes factors.

    Conclusions:

    • The proposed Bayesian approach provides a powerful and practical method for analyzing data with extra-Binomial variability.
    • Approximate Bayes factors offer a computationally feasible alternative to exact Bayes factors.
    • The method is effective in real-world applications, including complex regression models.