<p><br>
On Mar 14, 2011 11:30 AM, "Nynke van der Laan" <<a href="mailto:nynkevanderlaan@gmail.com">nynkevanderlaan@gmail.com</a>> wrote:<br>
><br>
> Hello,<br>
> I have a question concerning searchlight analyses: Is there a build in<br>
> possibility in pyMVPA to add an extra variable to the pattern<br>
> analysis? E.g., if you have for each sample, next to the neuroimaging<br>
> data also skin conductance measures (1 per sample/scan). Would it be<br>
> possible to add this variable as a covariate to be able to see whether<br>
> this variable can improve the prediction accuracy?</p>
<p>Yes. You could use to two datasets, one for each signal type and hstack() them. This function is similar to the one in numpy but works with datasets.</p>
<p>Michael<br></p>