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

Retrospective analysis of sequential dose-finding designs.

John O'Quigley1

  • 1Institut Curie, 26 rue d'Ulm, 75005 Paris, France oquigley@math.ucsd.edu

Biometrics
|September 2, 2005
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

Use of roster charts in the investigation and prosecution of nurses suspected of inflicting deliberate harm on patients.

Medicine, science, and the law·2025
Same author

Gut feelings and the conviction of nurse Lucy Letby.

Nurse education in practice·2025
Same author

Sample Size Calculation in Dose Optimization Trials Using the Margin of Practical Non-Inferiority.

Statistics in medicine·2025
Same author

Correction to a correction of a statistical error.

Medicine, science, and the law·2025
Same author

Suspected serial killers and unsuspected statistical blunders.

Medicine, science, and the law·2024
Same author

Making sense of breast cancer risk estimates.

Genetic epidemiology·2024

The continual reassessment method (CRM) enables dose finding through dynamic updates. This study presents a consistent approach for retrospective analysis of CRM data, applicable to various sequential designs.

Area of Science:

  • Biostatistics
  • Clinical Trial Design
  • Pharmacometrics

Background:

  • The continual reassessment method (CRM) is a widely used adaptive dose-finding design in clinical trials.
  • CRM dynamically updates dose levels based on observed toxicity or efficacy data from all enrolled subjects.
  • Current CRM implementations face limitations in accurately analyzing retrospective data, especially when the underlying data-generating mechanism deviates from the CRM's model.

Purpose of the Study:

  • To develop a consistent methodology for retrospective analysis of data generated under the continual reassessment method (CRM).
  • To extend the applicability of retrospective analysis beyond the CRM to other sequential updating schemes.
  • To address the challenge of estimating target percentiles from retrospective data when the data-generating mechanism is arbitrary.

Related Experiment Videos

Main Methods:

  • The study proposes a novel statistical approach for retrospective analysis of CRM-generated data.
  • The methodology involves consistent estimation of target percentiles using model inversion.
  • The approach is designed to be robust even when the data-generating mechanism is not perfectly aligned with the CRM's simplified model.

Main Results:

  • A consistent method for retrospective analysis of CRM data has been established.
  • The proposed methodology demonstrates applicability to various sequential updating designs, not just CRM.
  • The findings enable accurate estimation of target percentiles from retrospective data, overcoming previous limitations.

Conclusions:

  • The developed methodology provides a robust solution for retrospective analysis in adaptive dose-finding studies.
  • This work enhances the utility of retrospective data in refining dose selection and understanding treatment effects.
  • The approach is generalizable to any sequential updating scheme linking dose levels to percentiles via model inversion.