*****  To join INSNA, visit  *****

I have data on the connections between individual members of community
organizations and various city offices.  I am conducting an analysis on the
effectiveness of community organizations.  So I would like to aggregate the
individual level data to the group.
What are people's opinions about the pros/cons of different techniques.  I
see at least three different options.
1.  One can create a dichotomous variable that equals one if at least one
group member has contacted a specific city office (0 otherwise).  The issue
with this option is that it loses information about the amount of
interaction between the group and the office.
2.  One can measure the total number of contacts between group members and a
particular office.  The issue here is that this measure will be affected by
the differing sizes of each group.
3.  One can measure the average number of contacts between group members and
a partiular office.  The advantage here is that this measure includes
information on the intensity of communication, but it is not biased by group
size.  The disadvantage is that it is not clear how to calculate measures of
effective ego network size or ego network efficiency when you begin with
Any thoughts.


Christopher Weare 
Associate Director, Civic Engagement Initiative

Research Associate Professor 
School of Policy, Planning, and Development 

VKC 371
University of Southern California 

Los Angeles, CA 90089-0626

213-740-4690 voice 

[log in to unmask] 


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