BookmarkSubscribeRSS Feed
Melk
Lapis Lazuli | Level 10

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

tx
21 0

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?

1 REPLY 1
pau13rown
Lapis Lazuli | Level 10

specify a value for year, i'm guessing 1 is not a legit value. Maybe this helps: https://communities.sas.com/t5/SAS-Statistical-Procedures/How-to-write-estimate-statements-for-conti...

SAS Innovate 2025: Call for Content

Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!

Submit your idea!

What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 1 reply
  • 1403 views
  • 0 likes
  • 2 in conversation