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

Estimating efficacy in clinical trials with clustered binary responses.

Jeffrey M Albert1

  • 1Department of Epidemiology and Biostatistics, School of Medicine BRB-G19, Case Western Reserve University, 10900 Euclid Avenue, Cleveland, OH 44120, USA. jma13@po.cwru.edu

Statistics in Medicine
|March 1, 2002
PubMed
Summary

This study extends efficacy analysis methods for clinical trials with non-compliance, particularly in cluster-randomized designs. Accounting for within-cluster correlations is crucial, even when small, for accurate treatment effect estimation.

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

Developmental Disorders in Children Recently Diagnosed With Cancer.

Pediatric blood & cancer·2026
Same author

Association of Medicaid expansion with colon cancer care: treatment patterns and survival in non-metastatic cases from state registry-claims data.

Cancer causes & control : CCC·2025
Same author

Maternal Childhood Trauma and Children's Developmental Course of Aggressive Behavior from Ages 4 to 12.

Psychology of violence·2025
Same author

A Rising Tide Raises All Ships: Was the Effect of Medicaid Expansion on Cancer Outcomes Similar Across Subgroups of Patients With Cancer on Medicaid?

AJPM focus·2025
Same author

Validity and reliability of Brier scoring for assessment of probabilistic diagnostic reasoning.

Diagnosis (Berlin, Germany)·2024
Same author

Multilevel Interventions and Dental Attendance in Pediatric Primary Care: A Cluster Randomized Clinical Trial.

JAMA network open·2024

Area of Science:

  • Biostatistics
  • Clinical Trials
  • Epidemiology

Background:

  • Non-compliance in clinical trials necessitates supplementary efficacy analyses beyond intent-to-treat.
  • Estimating treatment efficacy requires robust methods, especially with correlated data.

Purpose of the Study:

  • To extend the Sommer and Zeger (1991) method for efficacy estimation to accommodate within-cluster correlations.
  • To apply and evaluate this extended method in a village-randomized clinical trial for vitamin A supplementation in Indonesian children.

Main Methods:

  • Extension of a previously developed efficacy estimation method for binary outcomes and all-or-none compliance.
  • Incorporation of within-cluster correlation adjustments suitable for cluster-randomized designs.
  • Application to a real-world dataset from a vitamin A supplementation trial.

Related Experiment Videos

Main Results:

  • Within-cluster correlations in the Indonesian vitamin A trial data were minimal.
  • Adjusting for clustering did not significantly alter efficacy inferences in this specific trial.
  • Simulations confirmed the validity of the proposed method for finite sample sizes.

Conclusions:

  • The extended method effectively accommodates within-cluster correlations in efficacy analyses.
  • Even small within-cluster correlations can significantly impact efficacy inferences, highlighting the method's importance.
  • The approach is validated for practical use in cluster-randomized trials.