SCCN icon
SCCN Home
EEGLAB Home

Contemporary Statistical Methods Useful for EEG Analysis

Twelfth EEGLAB Workshop -- University of California San Diego (UCSD), La Jolla, CA - November 19, 2010

The videos of the Workshop talks have been divided into chapters to facilitate their use for online review and study. Press FS on the lower right corner of the video image to view the talk in full screen display. You may download the (.pdf) slides used in the talk here. To link another web page to a chapter N below, use the URL title of this page followed by #ChapterN .

This Talk -- David Groppe, postdoctoral researcher in UCSD's Kutaslab, introduces two resampling-based statistical methods (permutation tests and bootstrapping) and two methods for multiple-comparison correction (permutation-based control of the family-wise error rate and false discovery rate control) useful for EEG analysis.


Chapter 1: Brief review of popular parametric and nonparametric analytic statistical methods (e.g., t-tests, Mann-Whitney U test).


    For further reading:



  • Delorme, A. (2006) Statistical methods. Encyclopedia of Medical Devices and Instrumentation, Wiley Interscience, 6:240-264.

  • Zar, J.H. (2010) Biostatistical Analysis. 5th Edition, Pearson Prentice-Hall, Upper Saddle River, NJ.




Chapter 2: Introduction to permutation tests and bootstrapping.

    For further reading:







Chapter 3: Using permutation test-based family-wise error rate control and false discovery rate control to correct for mulitple comparisons (after initially answering some questions).

    For further reading:




Return to the Workshop Program, to Groppe's home page, or to the EEGLAB home page.