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

Small-sample confidence limits for parameters under inequality constraints with application to quantal bioassay.

M D Morris1

  • 1Mathematical Sciences Section, Oak Ridge National Laboratory, Tennessee 37831-8083.

Biometrics
|December 1, 1988
PubMed
Summary

New methods construct exact confidence limits for ordered distribution parameters, outperforming common procedures for discrete data. This approach offers competitive performance against asymptotic methods in binomial bioassays.

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

Phylogenetic analysis of full-length, early infection, hepatitis C virus genomes among people with intravenous drug use: the InC<sup>3</sup> Study.

Journal of viral hepatitis·2016
Same author

Analysis of resistance-associated substitutions in acute hepatitis C virus infection by deep sequencing across six genotypes and three continents.

Journal of viral hepatitis·2016
Same author

A longitudinal study of hepatitis C virus testing and infection status notification on behaviour change in people who inject drugs.

Journal of epidemiology and community health·2015
Same author

Fracture healing with alendronate treatment in the Brtl/+ mouse model of osteogenesis imperfecta.

Bone·2013
Same author

Social, economic, and psychological impacts of MDR-TB treatment in Tijuana, Mexico: a patient's perspective.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2013
Same author

Characterization of the effects of postextraction treatments on human dentin-resin interface by micro-Raman spectroscopy.

Journal of biomedical optics·2012

Area of Science:

  • Biostatistics
  • Statistical Inference
  • Quantitative Biology

Background:

  • Constructing confidence limits for parameters in ordered distributions is crucial for statistical analysis.
  • Existing methods may lack precision or exhibit coverage issues, particularly for discrete distributions and small sample sizes.

Purpose of the Study:

  • To present a novel family of methods for generating confidence limits for ordered distribution parameters.
  • To evaluate the exactness, conservativeness, and tightness of these new confidence limits compared to existing procedures.
  • To demonstrate the application and efficacy of these methods in binomial quantal bioassay.

Main Methods:

  • Development of a new family of statistical methods for confidence limit construction under parameter ordering assumptions.

Related Experiment Videos

  • Theoretical analysis to establish exactness or conservativeness for finite samples.
  • Comparative evaluation against a common single-sample procedure for discrete distributions.
  • Application to a binomial quantal bioassay with a nondecreasing dose-response function.
  • Simulation studies to compare performance with asymptotic methods.

    • Main Results:

    • The proposed methods yield exact or conservative confidence limits for finite samples.
    • For discrete distributions, the new methods provide at least as tight confidence limits as a standard single-sample procedure.
    • In binomial quantal bioassay, the new approach demonstrates competitive performance against asymptotic methods, especially when asymptotic methods maintain nominal error rates.
    • Simulation results highlight potential discrepancies in competing asymptotic methods for small binomial samples (up to size 30).

    Conclusions:

    • The presented methods offer a robust approach for constructing confidence limits for ordered parameters.
    • These methods are particularly advantageous for discrete distributions and binomial bioassay applications.
    • The new approach provides reliable and often tighter confidence intervals, addressing limitations of existing techniques.