| Date: | Fri, 29 Jul 2005 12:01:26 +0100 |
|---|
| 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: Hierarchical Ordinal Regression |
|---|
|
| In-Reply-To: | <26078234-D96F-46D7-BDD6-3ACC56EA935D@rockhurst.edu> |
|---|
| Content-Type: | text/plain; charset=ISO-8859-1; format=flowed |
|---|
Indirectly. You need to do it manually - run the analysis without the
variables, then run the analysis with. The chi-square statistic is the
measure of change. The difference in the chi-squares is distributed as
a chi-square, with the df being the difference in df between the models.
(Which is equal to the number of variables that were added in the
second model.)
JM
Myles P. Gartland wrote:
> I wish to perform a hierarchical regression model. In the linear
> regression option, I can enter different blocks of variables and then
> measure the R-Square change.
>
> Can you do a similar procedure in the ordinal regression model? My DV
> is a 5 point satisfaction scale.
>
--
Jeremy Miles
mailto:jnvm1@york.ac.uk http://www-users.york.ac.uk/~jnvm1/
Dept of Health Sciences (Area 4), University of York, York, YO10 5DD
Phone: 01904 321375 Mobile: 07941 228018 Fax 01904 321320
| 
