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

On non-inferiority analysis based on delta-method confidence intervals.

Mark D Rothmann1, Hsiao-Hui Tsou

  • 1Division of Biometrics I, OB/OPSS/CDER, Food and Drug Administration, Rockville, Maryland 20857, USA. Rothmannm@cder.fda.gov

Journal of Biopharmaceutical Statistics
|August 19, 2003
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

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

Phenotypic Response Surfaces-Guided Optimization (PRS-OPT) of Propolis-Metformin-Regorafenib Combination Therapy for MASLD-Associated Hepatocellular Carcinoma.

Oncology research·2026
Same author

SLOG versus modified FOLFIRINOX as first-line treatment for advanced pancreatic cancer: A randomized phase II trial (TCOG T5217).

European journal of cancer (Oxford, England : 1990)·2026
Same author

Excess Mortality and Containment Performance During the COVID-19 Pandemic: Evidence From 34 Countries.

American journal of public health·2025
Same author

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

Statistics in medicine·2025
Same author

Search Volume of Insomnia and Suicide as Digital Footprints of Global Mental Health During the COVID-19 Pandemic: 3-Year Infodemiology Study.

Journal of medical Internet research·2025

Active-controlled trials are crucial when placebos are unethical. This study evaluates non-inferiority testing procedures for time-to-event data, finding Fieller confidence intervals maintain type I error rates, unlike delta-method procedures.

Area of Science:

  • Clinical Trials Methodology
  • Biostatistics
  • Pharmacoeconomics

Background:

  • Active-controlled trials are standard when placebo use is unethical.
  • Non-inferiority trials assess if new treatments retain a fraction of established therapy effects.
  • Meta-analyses inform the expected effect size of active controls.

Purpose of the Study:

  • To evaluate type I error rates of delta-method confidence intervals for non-inferiority testing with time-to-event endpoints.
  • To identify conditions under which these procedures maintain desired error rates.
  • To compare delta-method procedures with Fieller confidence intervals.

Main Methods:

  • Examined type I error probability for delta-method procedures under assumed active-control effect models.

Related Experiment Videos

  • Analyzed time-to-event endpoints using hazard ratios.
  • Contrasted delta-method 95% confidence intervals with Fieller 95% confidence intervals.

    • Main Results:

    • Delta-method procedures do not consistently maintain desired type I error rates.
    • One application (Cardiorenalogy) maintained error rates, while another (Oncology) did not.
    • Fieller 95% confidence intervals maintain desired approximate type I error rates.

    Conclusions:

    • Fieller confidence intervals offer a reliable method for non-inferiority testing with time-to-event data.
    • Caution is advised when using delta-method procedures due to potential type I error inflation.
    • Accurate modeling of active-control effects is critical for valid non-inferiority trial interpretation.