[Eeglablist] Is there any limit on removal of ICA components

Makoto Miyakoshi mmiyakoshi at ucsd.edu
Wed Nov 14 15:59:05 PST 2012


Dear Chaitanya,

There is no limit, so you can determine how many.

If you have 32 channels, discarding 16 ICs does NOT mean you discarded
50 % of data. This is because each IC has different weight. After ICA,
ICs are sorted from high variance to low variance. Discarding first
1-5 ICs could easily discard more than 50 % of variance. Usually, eye
blinks and EOGs appear within first 5 or 10 ICs, and discarding them
greatly reduces data variance.

If you want to evaluate each IC's variance, use envtopo. This can be
used from GUI.

Makoto

2012/11/4 chaitanya bhavaraju <chaitanya1686 at gmail.com>:
> Dear EEGLAB users,
>
> I would like to know is there any specific limit on the removal of ICA
> components. I have 32 channel data and i am getting 32 ICA components,when i
> am try to identify the eye, muscle ,other components i am worried about
> removing too many components from the data. Please suggest me a solution.
>
> thank you,
> Chaitanya
>
> _______________________________________________
> 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



-- 
Makoto Miyakoshi
JSPS Postdoctral Fellow for Research Abroad
Swartz Center for Computational Neuroscience
Institute for Neural Computation, University of California San Diego



More information about the eeglablist mailing list