Date:         Sun, 21 Oct 2007 20:46:19 -0400
Reply-To:     "Andrea Roofe (FIU)" <andrea.roofe@FIU.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "Andrea Roofe (FIU)" <andrea.roofe@FIU.EDU>
Subject:      data reduction prior to use of HLM
In-Reply-To:  <200710220013.l9LAmxBL024994@mailgw.cc.uga.edu>
Content-Type: text/plain; charset="us-ascii"

Hello everyone,

I'm working with a pooled cross-sectional time series covering 9 countries,
and more than 40 predictors, representing multiple indicators of 6
constructs.  Is Principal Components Analysis considered an appropriate form
of data reduction for use with a hierarchical linear model?    If yes, can
you direct me to an appropriate resource which will show me how to apply the
results of a PCA to HLM.  I'd be grateful for any SAS resources that could
help me carry out this analysis using SAS/STAT or SAS/Enterprise Guide.
This is my first time working with HLM.



Thank you.

Andrea Roofe