Hi all,
So here's my problem:
I have a sample of just over 100 participants with repeated measures that
have been collected over two waves (one year apart). I was wanting to
create a theoretical model of the relationships between the measured
variables but don't believe I have a large enough sample for Structural
Equation Modelling (with latent variables etc). I've looked at a
correlational matrix and the correlations appear to be following my
hypotheses.
My question:
Is it possible to use some kind of regression analyses to create such a
model or is the sample size prohibitive? I've reduced my model so far to 8
constructs which have each been measured twice. I'm aware that I may need
to simplify this model further if I want to test it statistically. Any
advice on procedures I could use?
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Locked
