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

Using the maximum test statistic in the two-period crossover clinical trial.

A R Willan1

  • 1National Cancer Institute of Canada, Clinical Trials Group, Kingston, Ontario.

Biometrics
|March 1, 1988
PubMed
Summary

In crossover trials with suspected carryover, using only first-period data for parallel analysis is common. However, crossover analysis is more powerful if residual carryover is minimal, offering better statistical power.

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

Cesarean delivery or induction of labor in pre-labor twin gestations: a secondary analysis of the twin birth study.

BMC pregnancy and childbirth·2020
Same author

Planned Cesarean or planned vaginal delivery for twins: secondary analysis of randomized controlled trial.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2019
Same author

Urinary stress incontinence and other maternal outcomes 2 years after caesarean or vaginal birth for twin pregnancy: a multicentre randomised trial.

BJOG : an international journal of obstetrics and gynaecology·2018
Same author

Maternal outcomes at 3 months after planned caesarean section versus planned vaginal birth for twin pregnancies in the Twin Birth Study: a randomised controlled trial.

BJOG : an international journal of obstetrics and gynaecology·2015
Same author

Maternal and infant predictors of attendance at Neonatal Follow-Up programmes.

Child: care, health and development·2013
Same author

Haemophilia prophylaxis: how can we justify the costs?

Haemophilia : the official journal of the World Federation of Hemophilia·2012

Area of Science:

  • Clinical Trial Design
  • Biostatistics
  • Pharmacometrics

Background:

  • Two-period crossover trials are susceptible to residual carryover effects.
  • Standard practice often involves analyzing only first-period data for parallel designs when carryover is suspected.
  • This approach may lead to a loss of statistical power compared to full crossover analysis.

Purpose of the Study:

  • To evaluate the power and precision of different analytical approaches in two-period crossover trials with suspected residual carryover.
  • To determine the conditions under which crossover analysis remains more powerful than parallel analysis.
  • To provide guidance on selecting the optimal analysis strategy based on empirical data.

Main Methods:

  • The study compares the statistical power of crossover and parallel analyses.

Related Experiment Videos

  • It introduces a condition based on residual carryover proportion and intrasubject correlation coefficient (rho) to guide analysis selection.
  • Approximate nominal significance levels are presented for maintaining desired Type I error rates when using the maximum test statistic.

    • Main Results:

    • Crossover analysis is statistically more powerful than parallel analysis when residual carryover is less than a specific threshold (2-sqrt(2(1-rho))).
    • Choosing the analysis based on the larger test statistic is equivalent to empirically evaluating this condition.
    • The analysis based on the maximum test statistic offers a balance between the power of crossover and the robustness of parallel analysis.

    Conclusions:

    • In two-period crossover trials with suspected residual carryover, the choice of analysis impacts statistical power.
    • A data-driven approach, selecting the analysis with the maximum test statistic, can optimize power while controlling Type I error.
    • This strategy provides a more powerful and precise alternative to exclusively using parallel analysis when carryover is present but not prohibitive.