Date: Tue, 6 Sep 2005 11:31:10 -0700
Reply-To: Dale Glaser <email@example.com>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Dale Glaser <firstname.lastname@example.org>
Subject: Re: Test - Retest
Content-Type: text/plain; charset=iso-8859-1
Jessica.......the simplest way to assess test retest is just to correlate the assumedly summative scores r (t1t2). However, since you mentioned validity, I'm not sure to what extent you have 'validated' your assessment device. If there are scales/subscales, has a factor analytic (or kindred) approach been pursued? And, since this is administered on two occasions, you may want to test the invariance of the factorial structure across time using structural equation modeling (SEM) software. ...........so unless the psychometric properties of the instrument have been clearly established, starting off with a test of stability via test-retest correlation may not be appropriate.
"Franson, Jessica Leigh" <fransonj@UWEC.EDU> wrote:
I'm working with someone who recently conducted some survey research.
He surveyed the same group of people twice over a certain period of time
and wants to test the validity of the results by comparing both data
sets. What's the best way to go about this?
Note: New email is email@example.com
Instructional Technologist/Statistical Software Consultant
Network for Excellence in Teaching
Learning &Technology Services
University of Wisconsin-Eau Claire
Dale Glaser, Ph.D.
4003 Goldfinch St, Suite G
San Diego, CA 92103