<div dir="ltr">Thanks for the answer. <div>Suppose we trust 100% the conjunction analysis. Why do you think MVPA ROI analysis result will require more analytic support? If I have an ROI within a network of regions, which decodes beyond chance, is it not an evidence that this region contains the relevant information?<div>
<br></div></div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Mon, Sep 23, 2013 at 4:40 PM, Yaroslav Halchenko <span dir="ltr"><<a href="mailto:debian@onerussian.com" target="_blank">debian@onerussian.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="im"><br>
On Mon, 23 Sep 2013, Vadim Axel wrote:<br>
<br>
> Hi,<br>
> There are two commonly used approaches to analyze the data of the<br>
> experiment below:<br>
> Simple design with two conditions (A and B), which �both activate large<br>
> network of well established regions (e.g. conjunction analysis of A ><br>
> baseline and B > baseline). The question is whether we can find neural<br>
> correlates of difference between the two.<br>
<br>
</div>the answer I guess is: yes -- we should be able to if "conditions are<br>
right" (power, etc)<br>
<div class="im"><br>
> Direct group-level analysis<br>
> comparison between A and B results in small activations (~5% of volume<br>
> comparing to commonality of conjunction analysis) and these activations<br>
> are located mostly outside the main network, all over the brain.<br>
<br>
</div>Remembering that statistics is there only to help us to support/reject<br>
our hypotheses, not really to be treated as "the ground truth", you<br>
might have set up your analysis to include only the "differential"<br>
activations which are within the main network, since that is where you<br>
believe activity or relevance is.<br>
<div class="im"><br>
> Given<br>
> that the result is dependent on p-value threshold, it looks like a<br>
> classical blobology. �Another approach is to select (independently) the<br>
> ROIs of the common network nodes and to run MVPA.<br>
<br>
</div>or even run MVPA on full brain happen you data has enough power to cope<br>
with such large initial feature space.<br>
<div class="im"><br>
> With this analysis I<br>
> successfully discriminate between the two conditions. So, two people<br>
> analyzing the same data can draw absolutely different conclusions: one<br>
> would say, that small regions X, Y, Z are the regions, which discriminate<br>
> between conditions A and B;<br>
<br>
</div>which given your results above would be sensible conclusion imho besides<br>
that I would have clarified that this set of regions is not necessarily<br>
exhaustive (thus "the regions" statement might be a bit too strong)<br>
<div class="im"><br>
> the other, in contrast, would say that since<br>
> both A and B activate common network<br>
<br>
</div>depending on what is implied by "activate common network" I might argue<br>
because it would be hard (if not impossible) to prove null hypothesis<br>
here that the network is the same for both A and B.<br>
<div class="im"><br>
> , the difference between the two lies<br>
> within this network (different patterns of activity). �<br>
<br>
> What approach is more reliable in your opinion?<br>
<br>
</div>as I stated above (if I got the question right), the 2nd approach would<br>
require (much) more analysis to support itself.<br>
<span class="HOEnZb"><font color="#888888"><br>
--<br>
Yaroslav O. Halchenko, Ph.D.<br>
<a href="http://neuro.debian.net" target="_blank">http://neuro.debian.net</a> <a href="http://www.pymvpa.org" target="_blank">http://www.pymvpa.org</a> <a href="http://www.fail2ban.org" target="_blank">http://www.fail2ban.org</a><br>
Senior Research Associate, Psychological and Brain Sciences Dept.<br>
Dartmouth College, 419 Moore Hall, Hinman Box 6207, Hanover, NH 03755<br>
Phone: <a href="tel:%2B1%20%28603%29%20646-9834" value="+16036469834">+1 (603) 646-9834</a> Fax: <a href="tel:%2B1%20%28603%29%20646-1419" value="+16036461419">+1 (603) 646-1419</a><br>
WWW: <a href="http://www.linkedin.com/in/yarik" target="_blank">http://www.linkedin.com/in/yarik</a><br>
<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></font></span></blockquote></div><br></div>