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

Procedures for testing the homogeneity of relative difference in sparse data.

Kung-Jong Lui1

  • 1Department of Mathematics and Statistics, San Diego State University, San Diego, CA 92182-7720, USA. kjl@rohan.sdsu.edu

Statistics in Medicine
|July 12, 2005
PubMed
Summary

This study introduces simple beta-binomial model procedures to test if treatment effects are consistent across patient groups in clinical trials with sparse data. The methods perform well for type I error control and power in various situations.

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 note on point estimation and interval estimation of the relative treatment effect under a simple crossover design.

Pharmaceutical statistics·2021
Same author

Urinary metabolites of furan in waterpipe tobacco smokers compared to non-smokers in home settings in the US.

Toxicology letters·2020
Same author

Exact Confidence Limits on Some New Measures of Concordance and Discordance in Binary Outcomes.

Therapeutic innovation & regulatory science·2020
Same author

Exact interval estimators for some commonly used measures of binary agreement.

Statistics in medicine·2019
Same author

Asymptotic and exact interval estimators of the common odds ratio under the sequential parallel comparison design.

Statistical methods in medical research·2018
Same author

Exact and asymptotic tests under the sequential parallel comparison design.

Pharmaceutical statistics·2018

Area of Science:

  • Biostatistics
  • Clinical Trial Methodology
  • Statistical Modeling

Background:

  • Quantifying excess treatment effects in clinical trials often uses relative difference.
  • Stratified analysis is common for controlling confounders, but homogeneity of relative difference across strata needs assessment.
  • Sparse data (many strata, few patients per stratum) presents challenges for homogeneity testing.

Purpose of the Study:

  • To develop and evaluate simple statistical procedures for testing the homogeneity of relative difference in sparse data settings.
  • To assess the performance of these procedures regarding type I error and statistical power.
  • To provide robust methods for analyzing clinical trial data with complex stratification.

Main Methods:

  • Development of test procedures based on the beta-binomial model.

Related Experiment Videos

  • Utilizing Monte Carlo simulations to evaluate performance under various conditions.
  • Assessment of type I error rates and statistical power of the proposed tests.

    • Main Results:

    • The proposed test procedures demonstrate good performance regarding type I error control.
    • The methods are effective in a variety of sparse data situations.
    • Evaluation of statistical power indicates the procedures' utility in detecting heterogeneity.

    Conclusions:

    • Simple beta-binomial based procedures are effective for testing relative difference homogeneity in sparse clinical trial data.
    • The developed methods offer robust and reliable tools for analyzing stratified data.
    • These procedures aid in ensuring the validity of summary estimates in complex clinical trial designs.