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

Creating non-parametric bootstrap samples using Poisson frequencies.

James A Hanley1, Brenda MacGibbon

  • 1Department of Epidemiology, Biostatistics and Occupational Health, McGill University, Montreal, Canada. James.Hanley@McGill.CA

Computer Methods and Programs in Biomedicine
|May 30, 2006
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

Counting sheep: Louis Pasteur and the first registered public vaccine trial.

European journal of epidemiology·2026
Same author

Risks and rates, and the mathematical link between them.

European journal of epidemiology·2025
Same author

Measurement variability of radiologists when measuring brain tumors.

European journal of radiology·2024
Same author

An evaluation of mindful clinical congruence in medical students after course-based teaching.

Canadian medical education journal·2024
Same author

Deaths averted: An unbiased alternative to rate ratios for measuring the performance of cancer screening programs.

Journal of medical screening·2023
Same author

Colonoscopy Screening and Colorectal Cancer Incidence and Mortality.

The New England journal of medicine·2023

This study introduces a shortcut for approximate non-parametric bootstrap samples, simplifying analysis for non-statisticians. The method shows comparable performance to standard bootstrap, with minimal differences in bootstrap standard errors for larger sample sizes.

Area of Science:

  • Statistics
  • Computational Statistics
  • Data Analysis

Background:

  • Non-statisticians often use high-level software packages.
  • Creating and analyzing bootstrap samples can be complex and computationally intensive.
  • Existing methods may require complex programming or the creation of new datasets.

Purpose of the Study:

  • To present a simplified method for generating and analyzing approximate non-parametric bootstrap samples.
  • To demonstrate the efficiency and accuracy of this shortcut method compared to traditional approaches.
  • To provide guidance on the applicability of non-parametric bootstrap samples.

Main Methods:

  • Utilizing Poisson frequencies instead of multinomial frequencies for observation counts.
  • Theoretical evaluation of bootstrap variance using a known closed-form estimator.

Related Experiment Videos

  • Empirical evaluation through two worked examples with complex sampling distributions.

    • Main Results:

    • The shortcut method demonstrates comparable performance to the standard bootstrap method.
    • For sample sizes of 50 or more, bootstrap standard errors differed by less than 1%.
    • The study illustrates scenarios where the proposed non-parametric bootstrap method is applicable and when it is not.

    Conclusions:

    • The proposed shortcut method offers an efficient and accurate alternative for approximate non-parametric bootstrap analysis.
    • This approach simplifies bootstrap analysis for non-statisticians, reducing the need for complex programming.
    • The findings provide practical insights into the application of non-parametric bootstrap techniques.