***** To join INSNA, visit http://www.insna.org *****
Dear Jay,

I would suggest considering a bivariate ERGM. This can be estimated with pnet.
bivariate ergm pnet
and you shall find various references.

Best wishes,
Tom

=========================================
Tom A.B. Snijders
Professor of Statistics and Methodology, Dept of Sociology, University of Groningen
Emeritus Fellow, Nuffield College, University of Oxford
http://www.stats.ox.ac.uk/~snijders

On Sun, Jan 8, 2017 at 10:49 PM, Hegde, Jay wrote:
---------------------- Information from the mail header -----------------------
Subject:      How to compare two directional networks of the same size?
-------------------------------------------------------------------------------

--_000_BN3PR03MB2212C94E55F0520A58A557DDC1650BN3PR03MB2212namp_
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

*****  To join INSNA, visit http://www.insna.org  *****

Hi Everyone,

We have two NxN connectivity matrices that define weighted, directional int=
eractions among the same set of N nodes under two different conditions, A a=
nd B. Since the interactions are directional, our connectivity matrices, wh=
ile being square, are asymmetric.

We want to identify the interactions that are significantly different betwe=
en the two conditions.  That is, how do the nodes talk to each other under =
condition A that do not do under condition B?  Of course, we want to do mor=
e than just calculating the difference between the two matrices. For one th=
ing, we know that if the matrices are symmetrical, there are toolkits for c=
omparing them.

But we're not sure how to compare our asymmetric matrices. Any ideas about =
(1) how to do it, and (2) any toolkits that implement the solution?

Thank you very much,
Jay

Jay Hegd=E9 PhD
Medical College of Georgia
Augusta University (formerly Georgia Regents University)
Augusta, GA 30912-2697

_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
UNSUBSCRIBE SOCNET in the body of the message.

--_000_BN3PR03MB2212C94E55F0520A58A557DDC1650BN3PR03MB2212namp_
Content-Type: text/html; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

*****  To join INSNA, visit http://www.insna.org  *****
<html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr=
osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" =
xmlns:m=3D"http://schemas.microsoft.com/office/2004/12/omml" xmlns=3D"http:=
//www.w3.org/TR/REC-html40">
<meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Diso-8859-=
1">
<meta name=3D"Generator" content=3D"Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
{mso-style-priority:99;
color:#954F72;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri",sans-serif;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext=3D"edit" spidmax=3D"1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext=3D"edit">
<o:idmap v:ext=3D"edit" data=3D"1" />
</o:shapelayout></xml><![endif]-->
<div class=3D"WordSection1">
<p class=3D"MsoNormal">Hi Everyone,<o:p></o:p></p>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
<p class=3D"MsoNormal">We have two NxN connectivity matrices that define <b=
><u>weighted</u></b>,
<b><u>directional</u></b> interactions among the <b><u>same set of N nodes<=
/u></b> under two different conditions, A and B. Since the interactions are=
directional, our connectivity matrices, while being square, are
<b><u>asymmetric</u></b>.<o:p></o:p></p>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
<p class=3D"MsoNormal">We want to identify the interactions that are signif=
icantly different between the two conditions.&nbsp; That is, how do the nod=
es talk to each other under condition A that do not do under condition B? &=
nbsp;Of course, we want to do more than just
calculating the difference between the two matrices. For one thing, we kno=
w that if the matrices are symmetrical, there are toolkits for comparing th=
em.<o:p></o:p></p>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
<p class=3D"MsoNormal">But we&#8217;re not sure how to compare our asymmetr=
ic matrices. Any ideas about (1) how to do it, and (2) any toolkits that im=
plement the solution?<o:p></o:p></p>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
<p class=3D"MsoNormal">Thank you very much,<o:p></o:p></p>
<p class=3D"MsoNormal">Jay<o:p></o:p></p>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
<p class=3D"MsoNormal">Jay Hegd=E9 PhD<o:p></o:p></p>
<p class=3D"MsoNormal">Medical College of Georgia<o:p></o:p></p>
<p class=3D"MsoNormal">Augusta University (formerly Georgia Regents Univers=
ity)<o:p></o:p></p>
<p class=3D"MsoNormal">Augusta, GA 30912-2697<o:p></o:p></p>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
</body>
</html>
_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
UNSUBSCRIBE SOCNET in the body of the message.

--_000_BN3PR03MB2212C94E55F0520A58A557DDC1650BN3PR03MB2212namp_--

_____________________________________________________________________ SOCNET is a service of INSNA, the professional association for social network researchers (http://www.insna.org). To unsubscribe, send an email message to [log in to unmask] containing the line UNSUBSCRIBE SOCNET in the body of the message.