Programming the statistical procedures from SAS

adding interaction terms to surveylogistic

Reply
Occasional Contributor
Posts: 5

adding interaction terms to surveylogistic

Hi, I have the following code for a logistic regression:

 

proc surveylogistic data = mydata;
strata STRATUM ; cluster SECU ; weight LBWGTR08 ;
class Female (ref="1") Ethnicity (ref="1") married08 (ref="1") SRHealthCat08 (ref = "1")  /param=ref ;
model SocPartAttendEventsDichot08 (Event = '1') = Age08 female ethnicity married08 SRHealthCat08 PopPct65up  / expb clodds ;

run ;

 

I want to add interaction terms and tried adding female*married08 like this:

 

proc surveylogistic data = mydata;
strata STRATUM ; cluster SECU ; weight LBWGTR08 ;
class Female (ref="1") Ethnicity (ref="1") married08 (ref="1") SRHealthCat08 (ref = "1")  /param=ref ;
model SocPartAttendEventsDichot08 (Event = '1') = Age08 female ethnicity married08 SRHealthCat08 PopPct65up female*married08 / expb clodds ;

run ;

 

But in the results, there was no odds ratio estimates for female*married08 - but this variable was included in other tables in the output. I'm not sure why there is no odds ratio - any help would be appreciated!

 

I'm using SAS Enterprise guide 6.1

New User
Posts: 1

Re: adding interaction terms to surveylogistic

I'm also having the same issue. Any comments will be appreciated. 

Ask a Question
Discussion stats
  • 1 reply
  • 192 views
  • 0 likes
  • 2 in conversation