[Eeglablist] Random selection of trials

Steve Luck sjluck at ucdavis.edu
Sun Apr 4 20:54:57 PDT 2010

As Tim Curran notes, if you measure mean amplitude rather than peak amplitude, your measure won't be biased by differences in the number of trials.  That is, the measures will be noisier in the conditions with fewer trials, leading to lower p-values, but this won't lead to artificial differences between conditions.

I'd like to thank Tim for referring people to the discussion of this issue in my book.  However, the discussion in the book is brief, and I have had many people ask me for a more extensive explanation.  I've therefore written an essay on this, which I plan to include in the next edition of my book.  To see this essay, simply point your browser to http://erpinfo.org/Members/sjluck/Mean_Peak_Noise.pdf.  I hope people find this helpful!

Steve Luck

> From: Kris Baetens <Kris.Baetens at vub.ac.be>
> Date: April 2, 2010 2:39:51 AM PDT
> To: eeglablist at sccn.ucsd.edu
> Subject: Re: [Eeglablist] Random selection of trials
> @ Tim curran: I have read Luck's book and I clearly see why using different trials in case of 
> peak measures (which we do not use) might be problematic. However, I can't quite understand why 
> average amplitudes would be 'immune' to this sort of problem; I think sensitivity to this 
> problem decreases as the number of time points in your average window increases? (In extremis:
> an average amplitude of two time points would, in the same logic as he discribes, still be extremely 
> vulnerable, no?) 

Steven J. Luck, Ph.D.
Interim Director, Center for Mind & Brain
Professor, Department of Psychology
University of California, Davis
Room 127
267 Cousteau Place
Davis, CA 95618
(530) 297-4424
sjluck at ucdavis.edu
Web: http://mindbrain.ucdavis.edu/people/sjluck
Calendar: http://www.google.com/calendar/embed?src=stevenjluck%40gmail.com&ctz=America/Los_Angeles

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20100404/e9d59f55/attachment-0001.html 

More information about the eeglablist mailing list