<html dir="ltr"><head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<meta name="GENERATOR" content="MSHTML 11.00.9600.16518">
<style id="owaTempEditStyle"></style><style title="owaParaStyle"><!--P {
MARGIN-BOTTOM: 0px; MARGIN-TOP: 0px
}
--></style>
</head>
<body ocsi="x">
<div style="FONT-SIZE: x-small; FONT-FAMILY: Tahoma; COLOR: #000000; DIRECTION: ltr">
<div>Hi</div>
<div><font face="tahoma">we've looked at Granger causality of ICAs<a></a> during motor imagery task, yes you can definitively see that some sources 'speak' to each other at certain points of time, related to the event while some other seem to be there always
(in mu rhythm) independent on the event.</font></div>
<div><font face="tahoma">Regards,</font></div>
<div><font face="tahoma">Alex</font></div>
<div dir="ltr"><font color="#000000" size="2" face="Tahoma"></font> </div>
<div id="divRpF692925" style="DIRECTION: ltr">
<hr tabindex="-1">
<font color="#000000" size="2" face="Tahoma"><b>From:</b> eeglablist-bounces@sccn.ucsd.edu [eeglablist-bounces@sccn.ucsd.edu] On Behalf Of Makoto Miyakoshi [mmiyakoshi@ucsd.edu]<br>
<b>Sent:</b> 19 February 2014 18:18<br>
<b>To:</b> Iman M.Rezazadeh<br>
<b>Cc:</b> EEGLAB List<br>
<b>Subject:</b> Re: [Eeglablist] Two step source connectivity analysis (as implemented in SIFT)<br>
</font><br>
</div>
<div></div>
<div>
<div dir="ltr">Dear Iman and all,
<div><br>
</div>
<div>So are you saying independent sources can Granger cause each other?</div>
<div><br>
</div>
<div>I agree with Joe and you. I'm not a specialist, but I would imagine (correct me if I'm wrong) that ICs are
<i>usually</i> independent <i>except</i> when they are perturbed event-relatedly. In such moments independence are transiently lost and ICs start to Granger cause each other... I tend to think in this way because stationarity depends on time scale. So in the
sense it's correct to say ICs are <i>not always</i> independent, because its independency changes from timepoint to timepoint. You can see this visualization with one of AMICA tools. However I haven't seen a log likelihood drop around the event, which contradicts
my explanation above, so I could be wrong somewhere. Multiple model AMICA does extract peri-event-onset periods as a different model though.</div>
<div><br>
</div>
<div>Note also that there is an issue of IC subspace within which ICs are always intra-dependent.</div>
<div><br>
</div>
<div>Makoto </div>
</div>
<div class="gmail_extra"><br>
<br>
<div class="gmail_quote">2014-02-19 0:53 GMT-08:00 Iman M.Rezazadeh <span dir="ltr">
<<a href="mailto:irezazadeh@ucdavis.edu">irezazadeh@ucdavis.edu</a>></span>:<br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">
<div lang="EN-US">
<div>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">I would like step in and add more comments which may be helpful (hopefully):<u></u><u></u></span></p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d"><u></u><u></u></span> </p>
<p class="MsoNormal"><a name="144495a6d99af755__MailEndCompose"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">The assumption of ICA is : The observed data is the sum of a set of inputs which have been mixed together in an
unknown fashion and the aim of ICA is to discover both the inputs and how they were mixed. So, after ICA we have some sources which are temporally independent. In other words, they are independent at time t McKeown, et al. (1998)<u></u><u></u></span></a></p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d"><u></u><u></u></span> </p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">However and based on Clive Granger talk at 2003 Nobel Laureate in Economics “The basic "Granger Causality" definition is quite simple. Suppose that we have
three terms, X<sub>t</sub>, Y<sub>t</sub>, and W<sub>t</sub>, and that we first attempt to forecast X<sub>t+1</sub> using past terms of Y<sub>t</sub> and W<sub>t</sub>. We then try to forecast X<sub>t+1</sub> using past terms of X<sub>t</sub>, Y<sub>t</sub>,
and W<sub>t</sub>. If the second forecast is found to be more successful, according to standard cost functions, then the past of Y appears to contain information helping in forecasting X<sub>t+1</sub> that is not in past X<sub>t</sub> or W<sub>t.
</sub>… Thus, Y<sub>t</sub> would "Granger cause" X<sub>t+1</sub> if (a) Y<sub>t</sub> occurs before X<sub>t+1</sub> ; and (b) it contains information useful in forecasting X<sub>t+1</sub> that is not found in a group of other appropriate variables.” So, in
Granger causality we try to relate time t+1 to t.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d"><u></u><u></u></span> </p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">So, ICA and Granger causality are not contradicting each other and finding causality btw sources would not have anything to do with source space or channel
space data. In my point of view, using ICA and source signal for Granger causality is good because you do not have to worry about the volume conductance problem. However, one can apply Granger causality in the channel space as well since the dipole localization
has its own limitations. One clue code be transforming the channel space data to current source density (CSD) format and then applying any causality/connectivity analysis you would like to study.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d"><u></u><u></u></span> </p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">Best<u></u><u></u></span></p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">Iman
<u></u><u></u></span></p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d"><u></u><u></u></span> </p>
<p class="MsoNormal"><b><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">-------------------------------------------------------------<u></u><u></u></span></b></p>
<p class="MsoNormal"><b><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">Iman M.Rezazadeh, Ph.D<u></u><u></u></span></b></p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">Research Fellow<u></u><u></u></span></p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">Semel Intitute, UCLA , Los Angeles<u></u><u></u></span></p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d">& Center for Mind and Brain, UC DAVIS, Davis<u></u><u></u></span></p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d"><u></u><u></u></span> </p>
<p class="MsoNormal"><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"; COLOR: #1f497d"><u></u><u></u></span> </p>
<p class="MsoNormal"><b><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"">From:</span></b><span style="FONT-SIZE: 11pt; FONT-FAMILY: "Calibri","sans-serif"">
<a href="mailto:eeglablist-bounces@sccn.ucsd.edu">eeglablist-bounces@sccn.ucsd.edu</a> [mailto:<a href="mailto:eeglablist-bounces@sccn.ucsd.edu">eeglablist-bounces@sccn.ucsd.edu</a>]
<b>On Behalf Of </b>Makoto Miyakoshi<br>
<b>Sent:</b> Tuesday, February 18, 2014 3:54 PM<br>
<b>To:</b> <a href="mailto:mullen.tim@gmail.com">mullen.tim@gmail.com</a><br>
<b>Cc:</b> <a href="mailto:eeglablist@sccn.ucsd.edu">eeglablist@sccn.ucsd.edu</a><br>
<b>Subject:</b> Re: [Eeglablist] Two step source connectivity analysis (as implemented in SIFT)<u></u><u></u></span></p>
<div>
<div class="h5">
<p class="MsoNormal"><u></u><u></u> </p>
<div>
<p class="MsoNormal">Dear Tim,<u></u><u></u></p>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
</div>
<div>
<p class="MsoNormal">Why don't you comment on the following question: If independent components are truly independent, how do causality analyses work?<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
</div>
<div>
<p class="MsoNormal">Dear Joe,<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
</div>
<div>
<p class="MsoNormal">Your inputs are too difficult for me to understand. In short, are you saying causality analysis works on independent components because they are not completely independent?<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
</div>
<div>
<p class="MsoNormal">Makoto<u></u><u></u></p>
</div>
</div>
<div>
<p class="MsoNormal" style="MARGIN-BOTTOM: 12pt"><u></u><u></u> </p>
<div>
<p class="MsoNormal">2014-02-18 15:46 GMT-08:00 Makoto Miyakoshi <<a href="mailto:mmiyakoshi@ucsd.edu">mmiyakoshi@ucsd.edu</a>>:<u></u><u></u></p>
<blockquote style="BORDER-TOP: medium none; BORDER-RIGHT: medium none; BORDER-BOTTOM: medium none; PADDING-BOTTOM: 0in; PADDING-TOP: 0in; PADDING-LEFT: 6pt; MARGIN-LEFT: 4.8pt; BORDER-LEFT: #cccccc 1pt solid; PADDING-RIGHT: 0in; MARGIN-RIGHT: 0in">
<div>
<p class="MsoNormal">Dear Bethel,<u></u><u></u></p>
<div>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
</div>
<div>
<p class="MsoNormal">> say A=sunrise and B=ice-cream-sale, then the ICA in EEGLAB should find that A is maximally temporaly independent from B.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
</div>
</div>
<div>
<p class="MsoNormal">ICA would find a correlation between sunrise and ice-cream-sale.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
</div>
<div>
<p class="MsoNormal">Makoto<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
<div>
<p class="MsoNormal">2014-02-10 4:57 GMT-08:00 Bethel Osuagwu <<a href="mailto:b.osuagwu.1@research.gla.ac.uk">b.osuagwu.1@research.gla.ac.uk</a>>:<u></u><u></u></p>
<div>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
<blockquote style="BORDER-TOP: medium none; BORDER-RIGHT: medium none; BORDER-BOTTOM: medium none; PADDING-BOTTOM: 0in; PADDING-TOP: 0in; PADDING-LEFT: 6pt; MARGIN-LEFT: 4.8pt; BORDER-LEFT: #cccccc 1pt solid; PADDING-RIGHT: 0in; MARGIN-RIGHT: 0in">
<p class="MsoNormal">Hi<br>
I am not an expert but I just want to give my own opinion!<br>
<br>
I do not think that temporal independence of two variables (A and B) violets causality between them as implemented in SIFT. In fact if say A=sunrise and B=ice-cream-sale, then the ICA in EEGLAB should find that A is maximally temporaly independent from B.
However we know there is causal flow from A to B.<br>
<br>
This is what I think, but I wait to be corrected so that I can learn!<br>
<br>
Thanks<br>
Bethel<br>
________________________________________<br>
From: <a href="mailto:eeglablist-bounces@sccn.ucsd.edu">eeglablist-bounces@sccn.ucsd.edu</a> [<a href="mailto:eeglablist-bounces@sccn.ucsd.edu">eeglablist-bounces@sccn.ucsd.edu</a>] On Behalf Of IMALI THANUJA HETTIARACHCHI [<a href="mailto:ith@deakin.edu.au">ith@deakin.edu.au</a>]<br>
Sent: 07 February 2014 01:27<br>
To: <a href="mailto:mullen.tim@gmail.com">mullen.tim@gmail.com</a><br>
Cc: <a href="mailto:eeglablist@sccn.ucsd.edu">eeglablist@sccn.ucsd.edu</a><br>
Subject: [Eeglablist] Two step source connectivity analysis (as implemented in SIFT)<u></u><u></u></p>
<div>
<div>
<p class="MsoNormal"><br>
Hi Tim and the list,<br>
<br>
I am just in need of a clarification regarding the ICA source reconstruction and the subsequent MVAR –based effective connectivity analysis using the components, which is the basis of the SIFT toolbox. I was trying to use this approach in my work but was questioned
on the validity using ICA and subsequent MVAR analysis by my colleagues.<br>
<br>
“When using independent component analysis (ICA), we assume the mutual independence<br>
of underlying sources, however when we try to estimate connectivity between EEG sources,<br>
we implicitly assume that the sources may be influenced by each other. This contradicts the<br>
fundamental assumption of mutual independence between sources in ICA [Cheung et al., 2010, Chiang et al., 2012, Haufe et al., 2009 ]. “<br>
<br>
So due to this reason different approaches such as MVARICA, CICAAR(convolution ICA+MVAR), SCSA and state space-based methods have been proposed as ICA+MVAR based source connectivity analysis techniques.<br>
<br>
<br>
· So, how would you support the valid use of SIFT ( ICA+MVAR as a two-step procedure) for the source connectivity analysis?<br>
<br>
<br>
· If I argue that I do not assume independent sources but rely on the fact that ICA will decompose the EEG signals and output ‘maximally independent’ sources and then, I subsequently model for the dependency, will you agree with me? How valid would
my argument be?<br>
<br>
It would be really great to see different thoughts and opinions.<br>
<br>
Kind regards<br>
<br>
Imali<br>
<br>
<br>
Dr. Imali Thanuja Hettiarachchi<br>
Researcher<br>
Centre for Intelligent Systems research<br>
Deakin University, Geelong 3217, Australia.<br>
<br>
Mobile : <a href="tel:%2B61430321972" target="_blank">+61430321972</a><u></u><u></u></p>
</div>
</div>
<p class="MsoNormal">Email: <a href="mailto:ith@deakin.edu.au">ith@deakin.edu.au</a><mailto:<a href="mailto:ith@deakin.edu.au">ith@deakin.edu.au</a>><br>
Web :<a href="http://www.deakin.edu.au/cisr" target="_blank">www.deakin.edu.au/cisr</a><<a href="http://www.deakin.edu.au/cisr" target="_blank">http://www.deakin.edu.au/cisr</a>><br>
<br>
[<a>cid:image001.jpg@01CF23FF.F8259940</a>]<br>
<br>
<br>
<br>
<br>
<br>
<br>
_______________________________________________<br>
Eeglablist page: <a href="http://sccn.ucsd.edu/eeglab/eeglabmail.html" target="_blank">
http://sccn.ucsd.edu/eeglab/eeglabmail.html</a><br>
To unsubscribe, send an empty email to <a href="mailto:eeglablist-unsubscribe@sccn.ucsd.edu">
eeglablist-unsubscribe@sccn.ucsd.edu</a><br>
For digest mode, send an email with the subject "set digest mime" to <a href="mailto:eeglablist-request@sccn.ucsd.edu">
eeglablist-request@sccn.ucsd.edu</a><u></u><u></u></p>
</blockquote>
</div>
</div>
</div>
<p class="MsoNormal"><span style="COLOR: #888888"><br>
<br clear="all">
<span><u></u><u></u></span></span></p>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
</div>
<p class="MsoNormal"><span><span style="COLOR: #888888">-- </span><u></u><u></u></span></p>
<div>
<p class="MsoNormal"><span style="COLOR: #888888">Makoto Miyakoshi<br>
Swartz Center for Computational Neuroscience<br>
Institute for Neural Computation, University of California San Diego</span><u></u><u></u></p>
</div>
</div>
</div>
</blockquote>
</div>
<p class="MsoNormal"><br>
<br clear="all">
<u></u><u></u></p>
<div>
<p class="MsoNormal"><u></u><u></u> </p>
</div>
<p class="MsoNormal">-- <u></u><u></u></p>
<div>
<p class="MsoNormal">Makoto Miyakoshi<br>
Swartz Center for Computational Neuroscience<br>
Institute for Neural Computation, University of California San Diego<u></u><u></u></p>
</div>
</div>
</div>
</div>
</div>
</div>
</blockquote>
</div>
<br>
<br clear="all">
<div><br>
</div>
-- <br>
<div dir="ltr">Makoto Miyakoshi<br>
Swartz Center for Computational Neuroscience<br>
Institute for Neural Computation, University of California San Diego<br>
</div>
</div>
</div>
</div>
</body>
</html>