Date: Thu, 25 Sep 2003 14:46:22 CEST
Reply-To: John.Antonakis@hec.unil.ch
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: John Antonakis <John.Antonakis@hec.unil.ch>
Subject: Re: Item-total correlation
Content-Type: text/plain; charset=ISO-8859-1
Hi Colin:
Thanks you for your posting. I was, though, looking for information on item-total correlation (i.e., the corrected correlation between the item and the average of the other items constituting the scale) and not on coefficient alpha (i.e., Cronbach alpha of internal consistency). Would you, or anyone else, happend to have any other sources of information on item-total correlations?
Regards,
John.
----Message d'origine----
>Date: Thu, 25 Sep 2003 08:23:23 -0400
>De: "Valdiserri, Colin" <Colin.Valdiserri@calphalon.com>
>Sujet: Re: Item-total correlation
>A: SPSSX-L@LISTSERV.UGA.EDU
>
>John,
>
>I would look at a couple articles by:
>
>Hulin, C. (2001). Can a reliability coefficient be too high? Journal of Consumer Psychology, 10 (1, 2), 56.
>
>Netemeyer, R. (2001). Can a reliability coefficient be too high? Journal of Consumer
>Psychology, 10 (1, 2), 56-57.
>
>These basically state the the inter-item correlation needs to be evaluated against the purpose of the scale, in academia .80 is usually low, in consumer based scales I have used ones with an Alpha as low as .65.
>
>The formula used to compute Alpha suggests that as the number of items in a scale increase, the correlation will increase and therefore will produce a large Alpha. This can lead to items in a scale being redundant and not just reliable.
>
>Colin M. Valdiserri
>Associate Consumer Scientist
>The Calphalon Group
>(419) 662-2378 - Office
>(419) 661-0223 - Fax
>colin.valdiserri@calphalon.com
>
>
>-----Original Message-----
>From: John Antonakis [mailto:John.Antonakis@hec.unil.ch]
>Sent: Wednesday, September 24, 2003 5:25 PM
>To: SPSSX-L@LISTSERV.UGA.EDU
>Subject: Item-total correlation
>
>
>Hi:
>
>Does anyone have a cite regarding what the minimum necessary value for an item-total correlation should be, which would demonstrate that the item is strongly related to the items consituting a particular scale? What would/should that value be?
>
>Thanks,
>John.
>
>*********************************************************************
>John Antonakis, Ph.D.
>Assistant Professor
>Department of Management, HEC
>University of Lausanne
>503-BFSH-1
>CH-1015 Lausanne-Dorigny
>Switzerland
>
>Tel: ++41 (0)21 692-3452
>Fax: ++41 (0)21 692-3495
>
>http://www.hec.unil.ch/hec/enseignement/professeurs/239?l=en
>http://www.hec.unil.ch
>********************************************************************
>
>
>
>
>THIS MESSAGE MAY CONTAIN INFORMATION THAT IS CONFIDENTIAL AND/OR PROTECTED BY LAW. IF THE READER OF THIS MESSAGE IS NOT THE INTENDED RECIPIENT, YOU ARE HEREBY NOTIFIED THAT ANY DISSEMINATION, DISTRIBUTION, COPYING OR COMMUNICATION OF THIS MESSAGE IS STRICTLY PROHIBITED. IF YOU HAVE RECEIVED THIS COMMUNICATION IN ERROR, PLEASE CONTACT THE SENDER IMMEDIATELY AND DELETE THE MESSAGE. PLEASE NOTE THAT ALTHOUGH WE WILL TAKE ALL COMMERCIALLY REASONABLE EFFORTS
>TO PREVENT VIRUSES FROM BEING TRANSMITTED FROM OUR
>SYSTEMS, IT IS THE RESPONSIBILITY OF THE RECIPIENT TO CHECK FOR AND PREVENT ADVERSE ACTION BY VIRUSES ON ITS OWN SYSTEMS .
>
>
*********************************************************************
John Antonakis, Ph.D.
Assistant Professor
Department of Management, HEC
University of Lausanne
503-BFSH-1
CH-1015 Lausanne-Dorigny
Switzerland
Tel: ++41 (0)21 692-3452
Fax: ++41 (0)21 692-3495
http://www.hec.unil.ch/hec/enseignement/professeurs/239?l=en
http://www.hec.unil.ch
********************************************************************
| 
