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

Sample size calculations with compliance information.

T Sato1

  • 1Institute of Statistical Mathematics, Tokyo 106-8569, Japan. shun@pbh.med.kyoto-u.ac.jp

Statistics in Medicine
|September 15, 2000
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

Elevation of hepatic levels of metallothionein and zinc in mice bearing experimental tumors.

Biochemical and biophysical research communications·1992
Same author

Relationship between inhibitor of extrathyroidal 5'-deiodinase activity and serum free fatty acid in children with nonthyroidal illness and acute ketosis.

Endocrinologia japonica·1992
Same author

Preferential activation of phospholipase A2 by low concentrations of phosphatidic acid with long-chain fatty acids in rabbit platelets.

Journal of biochemistry·1992
Same author

Innervation of an aberrant digastric muscle in the posterior thigh: stratified relationships between branches of the inferior gluteal nerve.

Journal of anatomy·1992
Same author

A simple stimulator for periodontal mechanoreceptors in human subjects.

Journal de biologie buccale·1992
Same author

Blockade of 2,4-dinitrophenol induced ATP sensitive potassium current in guinea pig ventricular myocytes by class I antiarrhythmic drugs.

Cardiovascular research·1992

This study introduces a new sample size formula for randomized trials that accounts for patient non-compliance, improving power in intention-to-treat analyses. The proposed method offers more accurate sample size calculations compared to conventional approaches.

Area of Science:

  • Biostatistics
  • Clinical Trial Design
  • Epidemiology

Background:

  • Non-compliance in randomized clinical trials (RCTs) reduces statistical power in standard intention-to-treat (ITT) analyses.
  • Accurate sample size calculations are crucial for RCTs to maintain adequate power and detect treatment effects.
  • Existing sample size methods may not adequately address the impact of varying compliance rates on statistical power.

Purpose of the Study:

  • To propose a novel sample size formula for binary outcomes in RCTs that incorporates compliance information.
  • To compare the proposed sample size calculation method with the conventional approach based on independent binomial distributions.
  • To evaluate the performance of the new formula across a wide range of clinical scenarios.

Main Methods:

Related Experiment Videos

  • Development of a new sample size formula for binary outcomes, explicitly considering compliance rates.
  • The proposed method is based solely on treatment randomization principles.
  • Comparison with the conventional method using 3100 combinations of baseline risks, treatment effects, compliance rates, test sizes, and powers.

    • Main Results:

    • The proposed sample size formula yields similar results to the conventional method for baseline risks between 0.4 and 0.6.
    • For baseline risks below 0.4, the proposed method generally requires larger sample sizes.
    • For baseline risks above 0.6, the proposed method tends to require smaller sample sizes when the true risk difference is negative.

    Conclusions:

    • The novel sample size formula provides a more nuanced approach to sample size calculation in RCTs by integrating compliance data.
    • This method can lead to more efficient and accurate sample size determination, particularly under varying baseline risk conditions.
    • Accounting for compliance in sample size calculations is essential for robust trial design and valid interpretation of results.