[Eeglablist] ICA & percent variance accounted for

Tyler Grummett tyler.grummett at flinders.edu.au
Fri Dec 12 16:26:51 PST 2014

You could always do an svd in matlab?

Then you could do an accumulative sum of the eigenvalues on the diagonal of the output (S I think). The components are usually in rank order, so the first PCA component would explain the most variance.


On 13 Dec 2014, at 9:42 am, Joëlle Albrecht <joelle.albrecht at hotmail.com<mailto:joelle.albrecht at hotmail.com>> wrote:

Dear EEGLAB-ers

I'm trying to find out, how much variance of the original data the components (computed by ICA) explain, but I'm not sure how to do this. (My goal is something like: Component 1 explains 60% of the variance in the original data. etc.)

1) I used the following function:

[pc,eigvec,sv] = runpca(EEG.data);
[proj pvaf] = compvar(EEG.data, pc, eigvec, components);

What exactly does the "percent variance accounted for (pvaf)" mean? For example if I got a pvaf of about 60, does this mean that this component explains 60% of the original data (or is it more complicated)? These pvaf's sum up to about 80, does this mean that 20% of the original data cannot be explained by all the components?

2) I used another function, too (after completing the ICA):

Again: What exactly do the pvaf's mean? Plus, these pvaf's are very different from the pvaf's I obtained with the function above. What is the difference? These pvaf's add to over 400 (whereas the ones from above sum up to only 80 which seems to be more reasonable to me), does this mean that the independent components overlap? The pvaf's resulting from this function (but not the ones from the one above)  are not monotonously decreasing - how are they sorted?

Thank you very much for the support!
Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu<mailto: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<mailto:eeglablist-request at sccn.ucsd.edu>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20141213/a42f0281/attachment.html>

More information about the eeglablist mailing list