[Eeglablist] Measure projection

[Makoto Miyakoshi]

Good to confirm that and thanks Nima for the quick response.

Makoto


On Sun, Aug 17, 2014 at 2:04 PM, Nima Bigdely Shamlo <
nima.bigdely at syntrogi.com> wrote:

> Makoto,
>
> You are correct: Measure Projection alleviates the *perceived *problem of
> not having an IC for a subject in a cluster. I do not think either having
> zero or more than one ICs in a cluster/domain are real problems and have
> written in detail about this in the past. In fact, forcing only a single IC
> in a cluster is a problem in my opinion. There is no reason for a subject
> to not have two IC with similar event-locked dynamics in the same cluster
> (remember IC are maximally independent over the whole experiment but could
> produce similar time-locked response).
>
> -Nima
>



-- 
Makoto Miyakoshi
Swartz Center for Computational Neuroscience
Institute for Neural Computation, University of California San Diego
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20140818/a0805684/attachment.html>