Print

Print


*****  To join INSNA, visit http://www.sfu.ca/~insna/  *****

Hello Socnetters,

I am searching for software programs to test statistically for the Group
Closeness  Index of my 60X60 symmetric matrix, conditional on the number
of arcs.

Any pointers will be very helpful.

Thank you.

Nilesh Saraf
College of Business
Florida Atlantic University

-----Original Message-----
From: Gavin Hougham [mailto:[log in to unmask]]
Sent: Wednesday, September 25, 2002 1:19 PM
To: [log in to unmask]
Subject: Comparing networks "concordance"


*****  To join INSNA, visit http://www.sfu.ca/~insna/  *****

Colleagues,

Let's say one generated a 500x500 sparsely filled matrix by method A
(citation references, say), and other 500x500 matrices (of the same
objects) by methods B, C, D.... Z (say, by post-hoc expert ratings on
some defined criteria).  Each of the n matrices can be separately
described by the usual set of networks metrics (e.g., to find clusters,
cliques, and so on...).

Would folks kindly direct me to some readings or examples of how to
compare the differently generated matrices of the same objects? If this
was a rating or concordance exercise (say in radiology), kappa-class
statistics might be used to compare the ratings of different referees of
the same objects ("yes, this film shows pathology"/"no, it doesn't").
What are similar approaches in SNA to describing networks concordance?

Hope I'm not missing the obvious, here.  Many thanks,,,,

Gavin Hougham

_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.sfu.ca/~insna/). To unsubscribe, send an
email message to [log in to unmask] containing the line UNSUBSCRIBE
SOCNET in the body of the message.

_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.sfu.ca/~insna/). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.