I am running a mixed model for a continuous measure with years as a continuous independent variable in the study. I also have treatment (1 or 0).
Here is my model:
proc mixed data=dat;
class id tx (ref='0');
model y=years|tx /s cl noint e;
random intercept years/type=un sub=id;
estimate 'Control' years 1 years*tx 0 1/cl;
estimate 'Treatment' years 1 years*tx 1 0/cl;
run;
Here is the class level information:SAS Output
But, my estimates are turning up opposite of what I expect. Are my estimate statements correct or can there be any other glitches I should be aware of?