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

Detecting dose-response using contrasts: asymptotic power and sample size determination for binomial data.

Frank Bretz1, Ludwig A Hothorn

  • 1Research Unit Bioinformatics, University of Hannover, Herrenhäuser Str. 2, 30419 Hannover, Germany. bretz@ifgb.uni-hannover.de

Statistics in Medicine
|October 31, 2002
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

The CRT-Estimands Framework for Cluster Randomized Trials.

JAMA·2026
Same author

Plant Kelch phosphatases are Ser/Thr phosphatases involved in cell cycle regulation.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

CRT-Estimands Framework: consensus based extension of the ICH E9(R1) addendum for cluster randomised trials.

BMJ (Clinical research ed.)·2026
Same author

STrategies for developing REseArch Methods guidance (STREAM): Protocol.

Journal of clinical epidemiology·2026
Same author

The role of statistical power in context: implications for regulatory practices.

Integrated environmental assessment and management·2026
Same author

Development of a consensus extension of the estimands framework for cluster randomised trials (CRT-estimands): results from an international Delphi study.

Trials·2025

This study enhances contrast tests for detecting dose-response relationships. New methods improve power calculations and sample size determination, offering practical applications in clinical trials.

Area of Science:

  • Biostatistics
  • Clinical Trial Design
  • Pharmacometrics

Background:

  • Stewart and Ruberg introduced contrast tests for dose-response detection, focusing on bivariate contrasts for healing rates.
  • Defining adequate coefficient sets for these tests presented a challenge.

Purpose of the Study:

  • To extend the work on contrast tests for dose-response relationships.
  • To derive asymptotic power expressions for single and multiple contrast tests.
  • To facilitate sample size calculations and improve numerical computations.

Main Methods:

  • Derived asymptotic power expressions for single and multiple contrast tests.
  • Re-expressed established trend tests as multiple contrast tests to simplify coefficient selection.
  • Utilized recent advancements in multivariate normal probability calculations, moving beyond simulation-based methods.

Related Experiment Videos

Main Results:

  • Developed modified power formulas enabling sample size calculations based on error rates, spontaneous rate, and dose-response shape.
  • Power study for small to moderate sample sizes indicated nominal power is a good approximation of actual power.
  • Demonstrated practical utility through a clinical trial example.

Conclusions:

  • The extended contrast test framework provides a robust method for analyzing dose-response relationships.
  • The derived power formulas and simplified test procedures enhance the practical application of contrast tests in clinical research.
  • Accurate sample size determination is now more feasible, improving the efficiency of clinical trial design.