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 estimation using repeated measurements on biomarkers as outcomes

A J Kirby1, N Galai, A Muñoz

  • 1Department of Epidemiology, Johns Hopkins School of Hygiene and Public Health, Baltimore, Maryland.

Controlled Clinical Trials
|June 1, 1994
PubMed
Summary

This study explores using longitudinal data in comparative trials to determine sample sizes. Accounting for autocorrelation in repeated measures can significantly reduce the required sample size for efficient trial design.

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

Some 1,2-diphenylethane derivatives as inhibitors of retinoic acid--metabolising enzymes.

Journal of enzyme inhibition and medicinal chemistry·2003
Same author

Novel spermine-based cationic gemini surfactants for gene delivery.

Chemical communications (Cambridge, England)·2002
Same author

Efficient intramolecular general acid catalysis: a preview from a crystal structure.

Chemical communications (Cambridge, England)·2002
Same author

1-[(Benzofuran-2-yl)phenylmethyl]triazoles as steroidogenic inhibitors: synthesis and in vitro inhibition of human placental CYP19 aromatase.

Anti-cancer drug design·2002
Same author

Estimating pKa values for pentaoxyphosphoranes.

Journal of the American Chemical Society·2002
Same author

Evaluation of 7-hydroxy-flavones as inhibitors of oestrone and oestradiol biosynthesis.

Journal of enzyme inhibition·2002

Area of Science:

  • Biostatistics
  • Clinical Trial Design
  • Longitudinal Data Analysis

Background:

  • Longitudinal data is frequently used in comparative trials.
  • Accurate sample size calculation is crucial for trial efficiency and validity.
  • The impact of autocorrelation in repeated measures on sample size is not always fully considered.

Purpose of the Study:

  • To examine methods for incorporating longitudinal data in comparative trial design and sample size calculations.
  • To demonstrate how autocorrelation of repeated measures affects sample size assessments.

Main Methods:

  • Utilized a statistical model with a regression structure for the mean trajectory.
  • Employed a two-parameter model for within-individual observation correlations: corr(yt,yt+s) = gamma s theta.

Related Experiment Videos

  • Illustrated methods using a two-group trial, varying correlation parameters (gamma and theta).

    • Main Results:

    • Incorporating autocorrelation structure in longitudinal data analysis can lead to more efficient trial designs.
    • Stronger autocorrelation between repeated measures results in a smaller required sample size.
    • The study quantifies the impact of autocorrelation parameters on sample size requirements.

    Conclusions:

    • Longitudinal data analysis methods, considering autocorrelation, enhance comparative trial design.
    • Optimized sample size calculations are achievable by accounting for the correlation structure of repeated measures.
    • This approach offers potential for more resource-efficient clinical trials.