Date:         Tue, 3 Dec 2002 20:51:35 +0000
Reply-To:     Jeremy Miles <jnvm1@york.ac.uk>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Jeremy Miles <jnvm1@york.ac.uk>
Subject:      Re: Standardized item alpha
Comments: To: "Snider-Lotz, Tom" <TSnider-Lotz@qwiz.com>
In-Reply-To:  <96EEA3FD5288C44B9F5FA17D259FD0D10320CB@qwizmail.qwiz.com>
Content-Type: text/plain; charset="us-ascii"; format=flowed

At 15:32 03/12/2002 -0500, Snider-Lotz, Tom wrote:
>In the Reliability routine, how is the standardized item alpha different
>from the traditional Cronbach's alpha?  I've got several psychometrics
>books and none discuss a "standardized" alpha.
>



Standardise the items first (i.e. make variances/SDs all equal).  If your
items have very different SDs, then one item will come to dominate the
scale.  The two versions of alpha are usually very similar.

JM



Jeremy Miles, Lecturer in Biostatistics,  Department of Health Sciences,
Alcuin College, University of York, YO10 5DD       mobile: 07941 228 018
mailto:jnvm1@york.ac.uk                http://www-users.york.ac.uk/~jnvm1
[working at home]                     http://www.jeremymiles.co.uk