***** To join INSNA, visit http://www.insna.org *****
***** To join INSNA, visit http://www.insna.org *****Hi Gilad,
I have used multilevel multiple membership models to solve similar problems.
a. I am looking at researchers affiliated with multiple projects. In this case, projects are treated as group level nodes rather than attributes. But I do think projects are the equivalent of countries in your study.
b. Then I looked at how the characteristics of each project jointly affect each individual who is affiliated with multiple projects, in terms of his/her behavior or structural position in the whole network. I am not sure if you are only looking at "the odds of the connection of two people in the same country" because the multilevel multiple membership models mainly look at the observed networks.
I have presented the work at SUNBELT this year. If you are interested in it, please let me know and I can send your the slides.
Guang Ying Mo
Department of Sociology
University of Toronto
> Date: Wed, 30 Apr 2014 00:33:53 +0300
> From: [log in to unmask]
> Subject: [SOCNE_____________________________________________________________________ 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.