[Eeglablist] ICA Debate

[Andreas Galka]

> We are having a heated debate here about EEGLAB and ICA.  When you use ICA
> to remove components in EEGLAB, does it remove these components only from
> the channels where the component is present or does it remove it from all
> channels?

>From all channels, in my understanding. The reason is that the mixing
matrix of the
ICA data model will typically have no elements that are exactly zero.
But for channels
for which the components are virtually absent, the elements will be
very small (compared
to other elements), and the change of those channels under artefact
removal will be
hardly visible.

Greetings,
Andreas Galka