Date:         Thu, 16 Sep 2010 13:55:00 -0400
Reply-To:     Gene Maguin <emaguin@buffalo.edu>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Gene Maguin <emaguin@buffalo.edu>
Subject:      Re: test for changes in ordinal variable
In-Reply-To:  <905E3A71-BE54-4F0F-BD49-451C89EEB547@mimectl>
Content-Type: text/plain; charset="us-ascii"

Hi Muir,

I disagree with your having computed difference scores. I'd agree that the
scores are categorical. Maybe strictly ordinal, maybe mostly ordinal, maybe
not. Being in the UK, you know more about the measure than me in the US ever
will. With deference to categorical analysts on the list and assuming that
you have some covariates to include, I'd think that something like plum
(ordinal logistic regression) or genlin might be more appropriate. Or,
nomreg (multichotomous logistic).

Gene Maguin


________________________________

From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of
Muir Houston
Sent: Thursday, September 16, 2010 1:33 PM
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: test for changes in ordinal variable


Listers,
More of a stats
I have a variables coded to major sub-groups of the UK Standard Occupational
Classification - the possible values are from '11' (Corporate Managers) to
'92' Elementary administration and service occupations.
(Ideal JobP1; Ideal JobP2; Expected JobP1; Expected Job2)

All possible values are:

11
12
21
22
23
24
31
32
33
34
35
41
42
51
52
53
54
61
62
71
81
82
91
92

Now what I want to do is calculate the degree of change over the two waves
of the survey. I have three locations (school A, B and C) and Gender and I
would be interested in whether there has been any significant change either
up or down the scale by school and by gender

The first thing I did was calculate change variables Delta1=( Ideal job
Phase 2)-(IdealJob Phase 1)
Delta2= (Expected job P2)-(Expected Job P1)
Delta3=(IdealJobP2)-(Expected JobP2)
Delta4=(Ideal JobP1)-(Expected JobP1)

values range from (-87) to (71)

What would you consider a suitable test to see if differences by gender and
school and over time exist?

thanks
Muir

Dr Muir Houston
Lecturer
DACE
Faculty of Education
University of Glasgow
0141-330-4699

=====================
To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD