Date:         Wed, 7 Oct 2009 10:53:11 -0400
Reply-To:     Peter Flom <peterflomconsulting@mindspring.com>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Peter Flom <peterflomconsulting@MINDSPRING.COM>
Subject:      Re: predicted probabilities in logistic model
Comments: To: ellen <ellenstats@GMAIL.COM>
Content-Type: text/plain; charset=UTF-8

ellen <ellenstats@GMAIL.COM> wrote
>I have a logistic regression model containing several co-variates.  I now
>wish to estimate the expected number of events for a variable that is not
>in the model but is in my data set.  Can I simply add up the predicted
>probabilities for the additional variable and if so how do I obtain the
>confidence interval, can I sum these too??
>
>Many thanks for any help you can give.

Do you mean an additional observation?  I don't see how this could work with additional variables.

If you do mean observations, then have you seen example 51.15 in the SAS/Stat documentation?  Title is "scoring data sets with the score statement".

First, run something ala this
<<<<
ods graphics on;
   proc logistic data=Crops plots(only)=effect(x=x3);
      model Crop=x1-x4 / link=glogit;
      score out=Score1;
   run;
   ods graphics off;
>>>

then
<<<
 proc logistic inmodel=sasuser.CropModel;
      score data=Crops out=Score3;
   run;
>>>

HTH

Peter

Peter L. Flom, PhD
Statistical Consultant
Website: www DOT peterflomconsulting DOT com
Writing; http://www.associatedcontent.com/user/582880/peter_flom.html
Twitter:   @peterflom