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


I am working with a data set which has friendship nominations for each
respondent.  I would like to make each egocentric friendship network an
event in an affiliation matrix.  Thus, some respondents will belong to more
than one event in the matrix.

The issue that I am struggling with is how to decide who belongs to what
event.  Assume A nominates B & C, B nominates A & C, C nominates A, B, & D,
and D nominates B & C.  Is it reasonable to say there are 3 friendship
events in my matrix (ABC, ABCD, DBC)?  My thought is yes.  Although there is
overlap between the events the addition or subtraction of a particular
member of the group may alter group behavior for instance.

This seems straight forward but I am relatively new to SNA and how to handle
the data correctly.  I know that I could set up the events as send networks,
received networks, reciprocated, etc.  Each of these would of course change
my affiliation matrix.  Is there a preferred method?  

Thank you for your thoughts.


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.