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

A note on P-values under group sequential testing and nonproportional hazards.

Daniel L Gillen1, Scott S Emerson

  • 1Department of Statistics, University of California, Irvine, California 92697, USA. dgillen@uci.edu

Biometrics
|July 14, 2005
PubMed
Summary

Group sequential designs require proper P-values for accurate clinical trial analysis. The Z-statistic ordering method for P-values is robust to time-varying treatment effects, unlike the analysis time ordering.

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

Statistical analysis of disease onset during lifespan with left truncation.

Biometrics·2026
Same author

Rejoinder to Commentaries on "A Perspective on the Appropriate Implementation of ICH E9(R1) Addendum Strategies for Handling Intercurrent Events".

Statistics in medicine·2026
Same author

Eligibility of men vs. women in Alzheimer's trials: Inclusive vs. representative.

The journal of prevention of Alzheimer's disease·2026
Same author

Interrupted Time Series Methods for Nonrandom Sampling Study Designs With Known Sampling Weights.

Statistics in medicine·2026
Same author

Semaglutide, weight loss, and cardiovascular outcomes in the SELECT trial - Authors' reply.

Lancet (London, England)·2026
Same author

Semaglutide and Cardiovascular Outcomes According to Baseline Aspirin Use: Analyses of the SOUL and SELECT Trials.

Diabetes, obesity & metabolism·2026

Area of Science:

  • Clinical Trials
  • Biostatistics
  • Statistical Methods

Background:

  • Group sequential designs enable interim analyses in clinical trials.
  • Standard P-value calculations can be invalid after sequential testing.
  • Proper P-value computation is crucial for maintaining trial integrity.

Purpose of the Study:

  • To compare the performance of analysis time (AT) and Z-statistic orderings for P-value computation in group sequential designs.
  • To evaluate how these methods handle delayed treatment effects on survival.

Main Methods:

  • Comparison of two P-value computation methods: analysis time (AT) ordering and Z-statistic ordering.
  • Evaluation of power functions under delayed and time-varying treatment effects.

Related Experiment Videos

Main Results:

  • Power under the AT ordering is significantly affected by delayed treatment effects.
  • Power functions derived from the Z-statistic ordering demonstrate robustness to time-varying treatment effects.

Conclusions:

  • The Z-statistic ordering provides a more reliable approach for calculating P-values in group sequential trials with time-varying treatment effects.
  • Researchers should consider the Z-statistic ordering when delayed treatment effects are anticipated.