Date: Wed, 28 Sep 2005 10:04:04 -0400
Reply-To: Art@DrKendall.org
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Art Kendall <Art@DrKendall.org>
Organization: Social Research Consultants
Subject: Re: averaged scales vs factor scores
In-Reply-To: <20050914143357.152.qmail@web34503.mail.mud.yahoo.com>
Content-type: text/plain; charset=ISO-8859-1; format=flowed
If you are creating scales, e.g., attitudes, achievement, values, using
unit weights and including only those items that load above some cut-off
(often +- .4) without splitting is conventional for several reasons.
These include the points that there is no intrinsic meaning to a zero
point, i.e., the numeric scaling is arbitrary; that the substantive
interpretation is easier; that divergent validity is enhanced; etc.
(Don't forget to reflect items that have negative loading before doing
your RELIABILITY.)
If you do not have scale items, there is no general convention.
However, standardizing the variables, and then proceeding as if you were
creating a scale has many of the same virtues as in scale construction.
As an exercise, save the factor scores from the various methods in
SPSS. Then create the scores using the summation method.
How well do the scores correlate?
Art
Art@DrKendall.org
Social Research Consultants
University Park, MD USA Inside the Washington, DC beltway.
(301) 864-5570
Plance Debouver wrote:
>I posted this with no lucky. How do I turn factor
>scores based on rotated loadings of FA procedures
>(scores obtained using regression method)into useful
>values for further analysis. I would like to compare 5
>groups of respondents.e.g nurses, doctors, Lab
>technicians, students. I am told that factor scores
>are not comparable across studies (they are sample
>specific) but summated or averaged scores are.
>
>Any recommendation for types of further analyses on
>factor scores or summed or averaged scales would be
>appreciated.
>
>plance.
>
>
>
>__________________________________
>Yahoo! Mail - PC Magazine Editors' Choice 2005
>http://mail.yahoo.com
>
>
>
>
| 
