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

Randomization tests for ERP topographies and whole spatiotemporal data matrices.

Eric Maris1

  • 1Nijmegen Institute of Cognition and Information, University of Nijmegen, 6500 HE Nijmegen, The Netherlands. maris@nici.kun.nl

Psychophysiology
|December 25, 2003
PubMed
Summary

Randomization tests offer a robust statistical alternative for analyzing complex electrophysiological data, outperforming bootstrap methods by providing exact probability values for event-related potential (ERP) studies.

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

Would You Agree If N Is Three? On Statistical Inference for Small N.

Journal of cognitive neuroscience·2025
Same author

Would you agree if N is three? On statistical inference for small N.

bioRxiv : the preprint server for biology·2025
Same author

A bicycle can be balanced by stochastic optimal feedback control but only with accurate speed estimates.

PloS one·2023
Same author

What to Do If N Is Two?

Journal of cognitive neuroscience·2022
Same author

Recommendations and publication guidelines for studies using frequency domain and time-frequency domain analyses of neural time series.

Psychophysiology·2022
Same author

Improving the sensitivity of cluster-based statistics for functional magnetic resonance imaging data.

Human brain mapping·2021

Area of Science:

  • Neuroscience
  • Statistics
  • Psychology

Background:

  • Classical statistical tests are often unsuitable for analyzing multichannel electrophysiological data, such as event-related potentials (ERPs).
  • Comparing complex spatiotemporal data matrices in ERP studies presents significant analytical challenges.
  • Resampling methods are needed to overcome the limitations of traditional statistical approaches in neuroscience research.

Purpose of the Study:

  • To introduce randomization tests as a powerful statistical alternative for analyzing electrophysiological data.
  • To demonstrate the superiority of randomization tests over bootstrap methods for ERP analysis.
  • To provide a comprehensive review of existing randomization tests for electrophysiological data and present novel methods.

Main Methods:

Related Experiment Videos

  • A review of the current literature on randomization tests for electrophysiological data.
  • Development and application of new randomization tests.
  • Analysis of two datasets: one from a psychopharmacological experiment and one from a visual word recognition ERP experiment.

Main Results:

  • Randomization tests are shown to be a suitable and effective method for comparing topographies and spatiotemporal data matrices in ERP studies.
  • The proposed randomization tests were successfully applied to real-world psychopharmacological and visual word recognition data.
  • Exact probability values (p values) can be obtained using randomization tests, a key advantage over bootstrap methods.

Conclusions:

  • Randomization tests provide an excellent and statistically rigorous alternative to classical tests for ERP data analysis.
  • These methods are particularly valuable for complex analyses involving multichannel measurements and spatiotemporal data.
  • The presented randomization tests offer enhanced analytical capabilities for electrophysiological research, facilitating precise statistical inference.