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


I have a dataset of information about 30 volunteers who work in a 
community owned shop.  The dataset contains a mix of binary information 
and valued information, the valued referring particularly to aspects of 
“how well do you know xxx” on a 5 point scale. The binary information 
covers such conditions as “do you cash up at the end of the working 

The volunteers work in fairly fixed pairings, (of which I know) in 
regular shifts over a 5 day week.  Thus I can expect to see Mary and 
Jane at 14:00 hours on Tuesday, and they will do a 2-hour shift.  
Occasionally, shift pairings get broken for personal or vacation 
reasons.  But by and large, the pairings are constant.  Each half day’s 
shifts are covered by a supervisor.  We can assume that most of the 30 
know each, but that there are levels of friendship, data I also have.

I also have two columns in this dataset with headings “who do you go to 
for procedural help in working in the shop?” and “who comes to you for 
procedural help about doing things in the shop?”.

I’m interested to find out:-
Who are the symmetrical pairs,
Who are the asymmetrical pairs?
Who are the null pairs?

It has been suggested that this information can be found by using p* 
routines.  Unfortunately I know nothing of these routines, but I do 
have access to Pajek and Siena, and I’m a user of UCINET.  I also use 
SPSS for typical (master’s) student quantitative work!

Can you please advise if there is a way other than p*, and if so what it is.

Would anyone be prepared, offline, to offer possibly more than just the 
odd email as I struggle to both get the answer I want, and learn how to 
do it again!


Roy Greenhalgh
M Res candidate
Univ of Bath, UK.

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.