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

Sizing clinical trials with variable endpoint event rates

L A Moyé1

  • 1University of Texas School of Public Health, Houston 77030, USA.

Statistics in Medicine
|November 14, 1997
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

A scoring system for ascertainment of incident stroke; the Risk Index Score (RISc).

Methods of information in medicine·2006
Same author

Ischemic stroke subtypes among Mexican Americans and non-Hispanic whites: the BASIC Project.

Neurology·2004
Same author

Evaluation of ethnic minorities and gender effects in clinical trials: opportunities lost and rediscovered.

Journal of the National Medical Association·2002
Same author

Trials within trials: confirmatory subgroup analyses in controlled clinical experiments.

Controlled clinical trials·2001
Same author

Low-density lipoprotein size, pravastatin treatment, and coronary events.

JAMA·2001
Same author

The platelet Pl(A2) and angiotensin-converting enzyme (ACE) D allele polymorphisms and the risk of recurrent events after acute myocardial infarction.

The American journal of cardiology·2001

Uncertainty in control group event rates can reduce cardiovascular trial power. This study introduces a method to formally adjust sample size calculations, treating the event rate as a random variable to improve trial design and interpretation.

Area of Science:

  • Cardiovascular Clinical Trials
  • Biostatistics
  • Clinical Trial Design

Background:

  • Sample size calculations are crucial for clinical trial design but are challenged by uncertainty in control group event rates.
  • Decreasing event rates in control groups during trials can lead to overestimation of required sample size, reducing statistical power and impacting interpretation.
  • Current methods lack a formal approach to adjust for anticipated decreases in control group event rates during the study's execution.

Purpose of the Study:

  • To develop a formal method for adjusting sample size calculations in cardiovascular clinical trials when control group event rates are uncertain.
  • To address the issue of potential decreases in control group event rates during a trial's course.
  • To provide a framework for more robust sample size determination in the face of event rate variability.

Related Experiment Videos

Main Methods:

  • Formulating sample size as a function of the control group event rate (theta).
  • Introducing a probability distribution for theta to account for its uncertainty.
  • Treating sample size as a random variable and computing its expectation and variance.

Main Results:

  • The proposed method allows for sample size adjustments based on probabilistic modeling of the control group event rate.
  • Analysis of sample size implications under various probability distributions for the event rate.
  • Demonstration of how accounting for event rate uncertainty can lead to more accurate power estimations.

Conclusions:

  • Formal adjustment for control group event rate uncertainty is necessary for reliable cardiovascular clinical trial sample size calculations.
  • Modeling the event rate with probability distributions provides a flexible approach to manage design-phase uncertainty.
  • This methodology enhances the robustness of clinical trial design and the interpretability of trial results.