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 the sample size for a t-test using an internal pilot.

J S Denne1, C Jennison

  • 1Department of Medical Statistics, De Montfort University, James Went Building, The Gateway, Leicester, LE5 9BH, U.K. jdenne@dmu.ac.uk

Statistics in Medicine
|July 17, 1999
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

Missing data and censoring in the analysis of progression-free survival in oncology clinical trials.

Journal of biopharmaceutical statistics·2013
Same author

Surveillance of community genital Chlamydia trachomatis testing in the East of England, 2008-2010.

Journal of public health (Oxford, England)·2011
Same author

Inequalities in access to knee joint replacements for people in need.

Annals of the rheumatic diseases·2004
Same author

The efficacy and safety of tadalafil: an update.

BJU international·2004
Same author

Inequalities in accessing hip joint replacement for people in need.

European journal of public health·2004
Same author

An evaluation of the safety and efficacy of simultaneous bilateral total knee arthroplasty.

The Journal of arthroplasty·2003

This study introduces a robust t-test using an internal pilot to accurately estimate sample size for two-treatment comparisons. This method improves control over type I and II error rates, enhancing statistical power in clinical trials.

Area of Science:

  • Biostatistics
  • Clinical Trial Design
  • Statistical Inference

Background:

  • Traditional t-test sample size calculations rely on pre-existing variance estimates, which can be inaccurate.
  • Misspecification of variance compromises the statistical power and reliability of t-tests.
  • Existing methods struggle to maintain robust error rate control when variance is uncertain.

Purpose of the Study:

  • To develop a more robust t-test for two-treatment comparisons using an internal pilot study.
  • To improve the accuracy of sample size determination in the presence of unknown variance.
  • To enhance the control of Type I and Type II error rates in clinical trial statistics.

Main Methods:

  • Implementation of Stein's two-stage test for adaptive sample size estimation.

Related Experiment Videos

  • Utilizing an internal pilot phase to estimate variance within the study.
  • Proposing a rule for optimal internal pilot size selection.

    • Main Results:

    • The proposed two-stage t-test procedure demonstrates closer control of Type I and Type II error rates compared to existing methods.
    • The internal pilot approach effectively addresses variance misspecification issues.
    • The suggested pilot size rule proves reasonable and efficient for the procedure.

    Conclusions:

    • The novel t-test procedure offers improved statistical robustness for two-treatment comparisons.
    • Accurate variance estimation via an internal pilot enhances the reliability of sample size calculations.
    • This method provides a more dependable approach to statistical testing in clinical research.