[prev in list] [next in list] [prev in thread] [next in thread] 

List:       sas-l
Subject:    Re: [Q] p values for inter-factor correlation
From:       Steve Gregorich <gregorich () PSG ! UCSF ! EDU>
Date:       1996-09-30 19:57:50
[Download RAW message or body]

Yoko,

You could use PROC CALIS to perform a
"Confirmatory" Factor Analysis.  The
results of the CFA would provide the
inter-factor correlation matrix as well
as standard errors.

Another approach would be to use the
bootstrap to estimate the standard errors
of the interfactor correlations.
Writing SAS code to perform bootsrap
sampling is fairly easy.  You can find
some example bootstrap code at the SAS
ftp site.

You may also be interested in the text:
Efron & Tibshirani (1993). An intoduction
to the bootstrap.  Chapman Hall.

HTH

Steve Gregorich
University of California, San Francisco
Prevention Sciences Group
74 New Montgomery Street
San Francisco, CA 94105  USA
gregorich@psg.ucsf.edu


In article <yokita-2809961321230001@slip-31-10.ots.utexas.edu>,
yokita@ccwf.cc.utexas.edu says...
>
>We can get inter-factor correlations by using "proc factor
>promax rotation."  However, p-values for these correlations
>are not available.  Are there any ways to get p-values
>for inter-factor correlations?

[prev in list] [next in list] [prev in thread] [next in thread]