[Eeglablist] Difference-Wave statistics

[Stephen Politzer-Ahles]

Hi Manuel,

Doing t-tests for all data points leads to a large multiple comparisons
problem (you are pretty much guaranteed to find false positives). For
better analysis methods, see Steve Luck's 2005 book *An Introduction to the
Event-Related Potential Technique* or Maris & Oostenveld's 2007
article in *Journal
of Neuroscience Methods*.

Best,
Steve Politzer-Ahles

On Mon, Sep 17, 2012 at 9:25 AM, Manuel Lemos Rodrigues
<m.lemos at ymail.com>wrote:

> Dear EEGLABlist members,
>
>
> I'm currently working on some oddball paradigm datasets and at this point
> analyzing difference-waves obtained by subtracting Grand-average ERPs of
> two conditions.
> So here is my question: Which way for statistical analysis do you
> recommend getting time ranges where the difference waves ( n = 10-15) are
> significant non-zero? I'm currently using two-sided subsequent ttests for
> all  datapoints ( Matlab function ttest).
> I noticed that  pop_comperp does have similiar funtionality for
> grand-averaged ERPs with one condition, but I get different results ( more
> conservative results).
>
>
> Thanks a lot and best regards,
>
> Manuel Lemos
> _______________________________________________
> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> To unsubscribe, send an empty email to
> eeglablist-unsubscribe at sccn.ucsd.edu
> For digest mode, send an email with the subject "set digest mime" to
> eeglablist-request at sccn.ucsd.edu
>



-- 
Stephen Politzer-Ahles
University of Kansas
Linguistics Department
http://www.linguistics.ku.edu/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20120917/9e036af9/attachment.html>