LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous (more recent) messageNext (less recent) messagePrevious (more recent) in topicNext (less recent) in topicPrevious (more recent) by same authorNext (less recent) by same authorPrevious page (March 2002)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Tue, 19 Mar 2002 09:39:46 +1100
Reply-To:     Sharon Morris <smorris@dbmcons.com.au>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Sharon Morris <smorris@dbmcons.com.au>
Subject:      Re: Different types of variables
Comments: To: David Lindsay <spss2002@sdresearch.com>
In-Reply-To:  <3C95C176.3562.1B237F@localhost>
Content-Type: text/plain; charset="Windows-1252"

Hi David,

I had a similar problem some time back with an evaluation we did of some chocolate products. I dealt with the problem by re-coding the "just right" type responses into a 3 point scale. For example, if you have very sweet, fairly sweet, just about right, not very sweet, not at all sweet, I would re-code them as follows:

very sweet --> poor fairly sweet --> average just about right --> just right not very sweet --> average not at all sweet --> poor

(I wouldn't use these particular labels, but just to give you an idea)

I then was able to use these recoded variables in a regression analysis. It is, of course, true that you are losing information by doing this, but in my particular case we had always done regressions for this particular client, and it was expected.

Just one way of using the data - I'm sure there are many more.

Sharon Morris Senior Project Manager DBM Consultants Pty Ltd 5-7 Guest Street Hawthorn VIC 3122 ph: 03 9819 1555 fax: 03 9819 9333

-----Original Message----- From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU]On Behalf Of David Lindsay Sent: Monday, 18 March, 2002 9:29 PM To: SPSSX-L@LISTSERV.UGA.EDU Subject: Different types of variables

In a product test there is an evaluation scale from "extremely good" to "extremely poor". There are also a number of scales that evaluate certain aspects of the product like colour that go from "very good" to "very poor". However there are a number of scales where the optimum is around the middle e.g. Very sweet, fairly sweet, just about right, not very sweet, not at all sweet.

I want to determine which of the scales drive/ correlate with the overall evaluation scale, but I realise that main scale is increasing so that optimum is at the end, whereas some the others have an optimum in the middle.

What analyses can I do?

--

david Lindsay-- David Lindsay http://www.SDResearch.com/


Back to: Top of message | Previous page | Main SPSSX-L page