|Date: ||Wed, 31 May 2006 11:15:52 +0200|
|Reply-To: ||Spousta Jan <JSpousta@CSAS.CZ>|
|Sender: ||"SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>|
|From: ||Spousta Jan <JSpousta@CSAS.CZ>|
|Subject: ||Re: Logistic Regression Question|
|Content-Type: ||text/plain; charset="US-ASCII"|
It may be still constant in the selected cases. And _not_ selected cases
are those filtered out or those where there are missing values in
variables used in the regression. In your case, I would study the
structure of missings first.
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of
Sent: Wednesday, May 31, 2006 1:50 AM
Subject: Logistic Regression Question
I am running a binary step-wise logistic regression model and I received
this notice for a predictor variable.
"The category variable VAR1 is constant for all selected cases. Since a
constant was requested in the model, it will be removed from the
My data are not constant for the variable in question.
Does anyone know why this occurred? Thanks in advance!