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

For a non-statistical but sometimes useful approach:
if you have a good number of time periods/matrices:
run the QAP correlations among all pairs of matrices.
Put those in a n(t) by n(t) matrix, with of course 0 in the diagonal.
Here, an off-diagonal value is the gamma or correlation association
measure between the matrix in one time period and the matrix in
another time period. Then MDS and perhaps even hierarchically cluster
that symmetric matrix. The MDS plot shows the "path" (and possibly
stages, if meaningful clustering) over time of relationships among the
matrices.
--
Ronald E. Rice
Department Chair
Arthur N. Rupe Professor in the Social Effects of Mass Communication
International Communication Association President 2006-2007
Co-Director, Carsey-Wolf Center
Dept. of Communication, 4005 Social Sciences & Media Studies Bldg (SSMS)
University of California, Santa Barbara, CA 93106-4020
Ph: 805-893-8696; Fax: 805-893-7102
[log in to unmask]; http://www.comm.ucsb.edu/people/academic/ronald-e-rice;
http://www.carseywolf.ucsb.edu


Quoting Alexander Semenov <[log in to unmask]>:

> ***** To join INSNA, visit http://www.insna.org *****
>
> Hi all!
>
> Although the article, mentioned by Brian is a platinum classic of the
> genre, I'm not sure if it's a good paper for jumpstart. Moreover, it uses
> pseudolikelihood approach, which is considered to be outdated now (as far
> as I know).
>
> As far as I know, Martin Everett presented his approach to comparison of
> the same network in different points of time based on QAP which in my
> humble opinion is more comprehendible than ERGM. Can't find any reference
> though, but it was presented in St. Petersburg 2 years ago.
>
> But if you feel comfortable with all that maths, stats and simulations, you
> should go straight to the papers and tools of Tom Snijders & Siena team and
> Carter Butts & statnet-based papers.
>
> Besides that I can suggest the following things on that topic (after a
> brief glance into awesome book "Studying Social Networks"):
>
> - Newcomb, Theodore M. "The acquaintance process." (1961).
> - Powell, Walter W., et al. "Network dynamics and field evolution: The
> growth of interorganizational collaboration in the life sciences1."
> *American
> journal of sociology* 110.4 (2005): 1132-1205.
> - Schnegg, Michael. "Blurred edges, open boundaries: The long-term
> development of a peasant community in rural Mexico." *Journal of
> anthropological research* (2007): 5-31.
>
> Hope that helps.
>
> Best,
> Alex.
>
>
>
> 2013/11/25 Brian Keegan <[log in to unmask]>
>
>> ***** To join INSNA, visit http://www.insna.org *****
>> My favorite paper across all of social network scholarship uses ERGMs for
>> comparative network studies with some fun findings about the similarity of
>> congressional co-sponsorship to monkey grooming and cow-licking: "Comparing
>> Networks Across Space and Time, Size and Species"
>> http://onlinelibrary.wiley.com/doi/10.1111/1467-9531.00118/abstract
>>
>> Mark Newman also has a review of several macroscopic network properties in
>> his 2003 review article (see page 10):
>> http://arxiv.org/pdf/condmat/0303516.pdf (citation to:
>> http://epubs.siam.org/doi/abs/10.1137/S003614450342480)
>>
>>
>> On Mon, Nov 25, 2013 at 9:56 AM, Mohammed Abufouda
>> <[log in to unmask]>wrote:
>>
>>> ***** To join INSNA, visit http://www.insna.org *****
>>>
>>> Hello SocNet,
>>>
>>>
>>>
>>> I want to study the possible similarities between two networks
>>> macroscopically ( on the structure level of the network) and
>>> microscopically ( on the node level ).
>>>
>>> Is there any related literature to start with ?
>>>
>>>
>>>
>>> My aim is to quantify the similarities among two networks, e.g., social
>>> network at time T1 and at time T2.
>>>
>>>
>>>
>>> Thanks in advance.
>>>
>>> Cheers,
>>>
>>>
>>>
>>> --
>>>
>>> Mohammed Abufouda
>>>
>>>
>>> _____________________________________________________________________
>>> 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.
>>
>>
>>
>>
>> --
>> Brian C. Keegan, Ph.D.
>> Post-Doctoral Research Fellow, Lazer Lab
>> College of Social Sciences and Humanities, Northeastern University
>>
>> [log in to unmask]
>> www.brianckeegan.com
>> M: 617.803.6971
>> O: 617.373.7200
>> Skype: bckeegan
>> _____________________________________________________________________
>> 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.
>>
>
> _____________________________________________________________________
> 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.
>

_____________________________________________________________________
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.