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


I am fairly green with statistics (I am conducting my master's thesis), so
bear with me. Especially, I have trouble conducting the tests in practice with
the software. I am conducting research on company dyads, and the data consists
of 7533 company pairs. I am strugling with the details of how I should deal
with the fact that the samples are not independent?

I need to calculate significance of correlation and logit (King's relogit
method to be more exact). I am using SPSS and STATA, and I would appreciate
practical tips on how to calculate the significance of correlations and
regression coefficients. Currently, almost all the significant levels in
correlations are p<0.001 due to the fact that n=7533.

I understood from several sources that 'pseudo t-tests' ot 'MRQAP' could be
used to evaluate the significance of coefficients, but I'm still quite lost on
how to do that in practice.

Thanks for advice!

Henri Schildt
Helsinki University of Technology

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.