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

Implementation of group sequential logrank tests in a maximum duration trial.

K K Lan1, J M Lachin

  • 1Biostatistics Research Branch, National Heart, Lung, and Blood Institute, Bethesda, Maryland 20892.

Biometrics
|September 1, 1990
PubMed
Summary

Accurate information times are crucial for group sequential trials using the logrank test. This study estimates information times in maximum duration trials, showing a patient exposure-based estimate is slightly conservative but usable for boundary construction.

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

Effect of GLP-1 and GIP on C-peptide secretion after glucagon or mixed meal tests: Significance in assessing B-cell function in diabetes.

Diabetes/metabolism research and reviews·2017
Same author

Application of robust estimating equations to the analysis of quantitative longitudinal data.

Statistics in medicine·2001
Same author

A flexible stochastic curtailing procedure for the log-rank test.

Controlled clinical trials·2000
Same author

Statistical considerations in the intent-to-treat principle.

Controlled clinical trials·2000
Same author

Computations for group sequential boundaries using the Lan-DeMets spending function method.

Controlled clinical trials·2000
Same author

Worst-rank score analysis with informatively missing observations in clinical trials.

Controlled clinical trials·1999

Area of Science:

  • Clinical Trials
  • Biostatistics
  • Statistical Methods

Background:

  • Group sequential procedures are vital for interim analyses in clinical trials to control Type I error rates.
  • Accurate information times (fractions of total events) are essential for the logrank test in these procedures.
  • Maximum duration trial designs, unlike maximum information designs, have an unknown total number of events at interim analyses.

Purpose of the Study:

  • To develop and evaluate methods for estimating information times in maximum duration group sequential trials.
  • To assess the bias and robustness of an information time estimate based on patient exposure.
  • To demonstrate the applicability of estimated information times in constructing group sequential boundaries using the Lan-DeMets procedure.

Main Methods:

Related Experiment Videos

  • Proposed an information time estimate based on the fraction of total patient exposure.
  • Investigated the bias of this estimate under exponential survival distributions.
  • Conducted numerical simulations to explore the robustness of the estimate with non-exponential survival data.
  • Applied the estimated information fraction within the Lan-DeMets procedure for boundary construction.

Main Results:

  • The patient exposure-based information time estimate is slightly negatively biased (conservative) under exponential survival.
  • The estimate demonstrates robustness when survival distributions deviate from exponential.
  • The Lan-DeMets procedure can effectively utilize the estimated information fraction for Type I error control, despite potential bias.
  • The study highlights the implications of using biased information estimates in group sequential procedures.

Conclusions:

  • An information time estimate based on patient exposure provides a practical approach for maximum duration group sequential trials.
  • This estimation method, while potentially biased, allows for valid construction of group sequential boundaries.
  • Careful consideration of information time estimation is necessary for reliable interim analyses and Type I error control in clinical trials.