Print

Print


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

Depending on how you went about your sampling, you may want to look into the work of Handcock & Gile (and their colleagues) at the Center for Statistics and the Social Sciences at the University of Washington.  They have several working papers that might be relevant. For example they have a working paper (no. 75) titled "Modeling Social Networks with Sampled or Missing Data."  In this paper they address how best to handle missing data that occurs "by design" (i.e., due to the sampling design) when estimating ERGMs.  

But, an alternative approach from ERG that I have used to analyze disparate ego-networks is hierarchical linear modeling.  The van Duijn et al (1999) and Wellman & Frank (2001) papers cited below, demonstrate the utility of this approach for studying the same kind of outcomes that ergm focuses on (i.e., the likelihood of a tie). The idea in using HLM to study ego-networks is that it accounts for the interdependencies within nested data (i.e., ties and alters embedded within egos and ego-networks) and enables you to identify independent factors specific to alter traits, tie traits, traits of the ego and traits of the ego-network.  Alter/tie variables are treated at the first level of analysis and ego/network variables are treated at level two. 

Just some food for thought...

Best,
Lindsay

van Duijn, M. A. J., van Busschbach, J. T., & Snijders, T. A. B. (1999). Multilevel analysis of personal networks as dependent variables. Social Networks, 21(2), 187-210. doi: 10.1016/s0378-8733(99)00009-x

Wellman, B., & Frank, K. (2001). Network Capital in a Multi-Level World: Getting Support from Personal Communities. In N. Lin, R. S. Burt & K. Cooke (Eds.), Social Capital: Theory and Research (p. 233+). Chicago: Aldine De Gruyter.
-------------------------------

On Mon, Feb 20, 2012 at 10:52 AM, Emese Domahidi <[log in to unmask]> wrote:
*****  To join INSNA, visit http://www.insna.org  *****

Dear all,

I am computing ERGM Models for ego networks of approximately 90 egos and
their alteri. The ego networks are not interconnected. I constructed an
overall model for all networks, controlling for different network
structures (e.g. edges and gwdsp) and different individual and dyadic
attributes. The model is converging and the model fit is ok.

My question is whether constructing an overall model instead of looking at
each ego network individually is an appropriate way to model ERGM for
ego networks. I would really appreciate comments on this approach as well as
literature recommendations on ego networks and ERG models.

Cheers, Emese

_____________________________________________________________________
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.



--
Lindsay Young
Doctoral Student
Northwestern University
Communication Studies
Media, Technology & Society Program


_____________________________________________________________________ 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.