Programming the statistical procedures from SAS

mixed model treatment group *placebo

Reply
Regular Contributor
Posts: 182

mixed model treatment group *placebo

[ Edited ]

Hi,

I'm do have a lot of experience working with mixed method models, so I hope someone can assist.

 

In the data, the placebo is where avisitn=4.  I need to get output by all treatment groups trt01pn * placebo (or where trt01pn=4).

Can someone help me modify this code or do I need to create some other variable for placebo?  Thanks!

 

proc mixed data = adeff method = reml;
where trtn ne 9 and avisit ne "Baseline";
by paramcd;
class usubjid trt01pn avisitn ;
model chg = trt01pn avisitn trt01pn*avisitn / solution ddfm=kr cl;
repeated avisitn / sub=usubjid type=sp(pow)(week);
lsmeans trt01pn * avsitn / cl;
lsmeans avisitn / cl;
ods output lsmeans = lsm_chg;
run;'

 

I've seen it done like this with 6 treatment groups but, not sure what this means.  Is there another way?

 

/* Day 7 comparisons */
estimate 'treat1-placebo7' trt01pn 1 0 0 -1 0 0
                                         trt01pn*avisitn  1 0
                                                                  0 0
                                                                  0 0
                                                                 -1 0
                                                                  0 0
                                                                  0 0 / divisor=1 e cl;

Ask a Question
Discussion stats
  • 0 replies
  • 118 views
  • 0 likes
  • 1 in conversation