<div dir="ltr"><div class="gmail_default" style="font-family:georgia,serif;font-size:large;color:rgb(0,0,0)">Hi Nick,<br><br></div><div class="gmail_default" style="font-family:georgia,serif;font-size:large;color:rgb(0,0,0)">I have now carried individual whole-brain searchlight with SVM and crossvalidation (using the 8 betas in condition A and B from each of the 8 runs as input, no Zscoring as each chunk only has 2 samples, 1 for A and 1 for B). <br><br>I reiterate I did this separately for each of the 19 subjects.<br><br>Â I then aimed to carry out a group analyses using the individual accuracy maps. to do this I merged the 19 nifti accuracy maps into a 4D file and run a one-sample t-test in FSL using randomise -i searchpred -o searchpredOneSampT -1 -v 5 -T. <br><br>Weirdly the output gives a group map with all brain voxels over p<0.001 !? which cannot be right...<br></div><div class="gmail_default" style="font-family:georgia,serif;font-size:large;color:rgb(0,0,0)"><br><br>Is there any advise please on performing the group level analyses on individual searchlight accuracy maps?<br></div><div class="gmail_default" style="font-family:georgia,serif;font-size:large;color:rgb(0,0,0)"><br>cheers<br>david<br></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Fri, Sep 12, 2014 at 12:10 PM, Nick Oosterhof <span dir="ltr"><<a href="mailto:nikolaas.oosterhof@unitn.it" target="_blank">nikolaas.oosterhof@unitn.it</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class=""><br>
On Sep 11, 2014, at 9:34 PM, David Soto <<a href="mailto:d.soto.b@gmail.com">d.soto.b@gmail.com</a>> wrote:<br>
<br>
> now my question is - would not zscoring solve the issue you mentioned?<br>
<br>
</span>Quite possibly so, but the only way to know is to try.<br>
<span class=""><br>
><br>
> I realise is not possible to zscore by chunks because these are the subjects<br>
> and only 2 samples....but I tried other zscoring schemes (i.e. by task condition<br>
> A vs. B or globally across the 38 samples) and still get null MVPA performance<br>
<br>
</span>That's not impossible, but still a bit curious.<br>
<span class=""><br>
><br>
> would there be any advantage in trying the tstats or zstats instead of the betas<br>
> as the former are already zscored?<br>
<br>
</span>It could, with t-stats there is usually less of an issue with outlier values.<br>
<div class="HOEnZb"><div class="h5"><br>
_______________________________________________<br>
Pkg-ExpPsy-PyMVPA mailing list<br>
<a href="mailto:Pkg-ExpPsy-PyMVPA@lists.alioth.debian.org">Pkg-ExpPsy-PyMVPA@lists.alioth.debian.org</a><br>
<a href="http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa" target="_blank">http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa</a><br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br><div dir="ltr"><a href="http://www1.imperial.ac.uk/medicine/people/d.soto/" style="color:rgb(17,85,204)" target="_blank">http://www1.imperial.ac.uk/medicine/people/d.soto/</a><br></div>
</div>