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

Assessing the robustness of randomization tests: examples from behavioural studies.

Pedro R. Peres-Neto1, Julian D. Olden

  • 1Department of Zoology, University of Toronto

Animal Behaviour
|February 15, 2001
PubMed
Summary

Behavioural researchers often face data issues. This study shows Monte Carlo simulations are crucial for evaluating statistical test robustness, unlike analytical methods, guiding reliable data analysis choices.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same journal

Hard to handle: infected house finches do not prefer easier-to-consume food.

Animal behaviour·2026
Same journal

The resident effect dominates over previous winner/loser experience in surface fish of the Mexican tetra.

Animal behaviour·2026
Same journal

Weakly electric fish use self-generated motion to discriminate object shape.

Animal behaviour·2026
Same journal

Galápagos yellow warblers differ in behavioural plasticity in response to traffic noise depending on proximity to road.

Animal behaviour·2026
Same journal

Solo songs, duets and territory defence across seasons in female Galápagos yellow warblers, <i>Setophaga petechia aureola</i>.

Animal behaviour·2026
Same journal

Bayesian updating for self-assessment explains social dominance and winner-loser effects.

Animal behaviour·2026

Area of Science:

  • Behavioral Science
  • Statistics
  • Statistical Power Analysis

Background:

  • Behavioral studies frequently encounter data violating parametric statistical assumptions.
  • Nonparametric and distribution-free methods are common but their robustness is under-evaluated.
  • Assessing robustness requires empirical methods like Monte Carlo simulations.

Purpose of the Study:

  • To evaluate the statistical power and Type I error rates of different statistical methods.
  • To demonstrate the necessity of Monte Carlo approaches over analytical methods for robustness assessment.
  • To provide a framework for behaviorists to select appropriate statistical tests.

Main Methods:

  • Detailed empirical protocols for estimating power and Type I error rates.

Related Experiment Videos

  • Application of protocols to analysis of variance (ANOVA) and regression/correlation designs.
  • Comparison of parametric, nonparametric (rank tests), and randomization tests.

    • Main Results:

    • Analytical methods are insufficient for evaluating statistical test robustness.
    • Monte Carlo approaches are essential for accurate assessment of power and Type I error.
    • Demonstrated application for ANOVA and regression/correlation analyses.

    Conclusions:

    • Monte Carlo simulations are vital for understanding statistical test reliability in behavioral research.
    • The study provides a framework for choosing robust statistical methods based on data characteristics.
    • Enhances the rigor of statistical analysis in behavioral science.