BookmarkSubscribeRSS Feed
☑ This topic is solved. Need further help from the community? Please sign in and ask a new question.
Diels_O
Obsidian | Level 7

Dear all, I met a question in PROC GEE analysis:

I want to add the center as a random effect to the model:

However, in my data, the ID was an independent on Center. (Refers to ID in each enter was not repeated)

data gee1;
input Center ID group Visit1-Visit4;
datalines;
1 1 1 0 0 0 0
1 2 1 0 0 0 0
1 3 1 1 1 1 1
1 4 0 1 1 1 0
1 5 1 1 1 1 1
1 6 0 0 0 0 0
2 7 0 1 0 0 1
2 8 1 0 1 0 1
2 10 0 1 1 1 1
2 11 1 0 1 1 0
2 12 1 0 0 1 1
2 13 0 1 1 0 0
;
data gee1;
set gee1;
Visit=1; Outcome=Visit1; output;
Visit=2; Outcome=Visit2; output;
Visit=3; Outcome=Visit3; output;
Visit=4; Outcome=Visit4; output;
run;
proc print; run;
Proc gee data = work.gee1 desc;
class id visit group(desc) outcome(desc) center;
model outcome = group / dist = binomial link = logit WALD TYPE3;
REPEATED subject = id(center)/ within = visit type = UN CORRW;
run;

And in the example in the https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.4/statug/statug_gee_examples01.htm,

The ID in each center is the same.

Can I use the reapeated subject = id(center) to input center as random effect?

If not, How Can I adjusted for center?

Sincerely hope I can get you help!

1 ACCEPTED SOLUTION

Accepted Solutions
StatDave
SAS Super FREQ

The GEE model does not use random effects, so you cannot add a random effect for CENTER in your PROC GEE model. If observations are considered correlated within IDs and observations from different IDs are considered uncorrelated, then SUBJECT=ID is what you need. And you are already adjusting for CENTER by including it as an effect in the MODEL statement.

View solution in original post

2 REPLIES 2
Diels_O
Obsidian | Level 7

Dear all, I met a question in PROC GEE analysis:

I want to add the center as a random effect to the model:

However, in my data, the ID was an independent on Center. (Refers to ID in each enter was not repeated)

data gee1;
input Center ID group Visit1-Visit4;
datalines;
1 1 1 0 0 0 0
1 2 1 0 0 0 0
1 3 1 1 1 1 1
1 4 0 1 1 1 0
1 5 1 1 1 1 1
1 6 0 0 0 0 0
2 7 0 1 0 0 1
2 8 1 0 1 0 1
2 10 0 1 1 1 1
2 11 1 0 1 1 0
2 12 1 0 0 1 1
2 13 0 1 1 0 0
;
data gee1;
set gee1;
Visit=1; Outcome=Visit1; output;
Visit=2; Outcome=Visit2; output;
Visit=3; Outcome=Visit3; output;
Visit=4; Outcome=Visit4; output;
run;
proc print; run;
Proc gee data = work.gee1 desc;
class id visit group(desc) outcome(desc) center;
model outcome = group / dist = binomial link = logit WALD TYPE3;
REPEATED subject = id(center)/ within = visit type = UN CORRW;
run;

And in the example in the https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.4/statug/statug_gee_examples01.htm,

The ID in each center is the same.

Can I use the reapeated subject = id(center) to input center as random effect?

If not, How Can I adjusted for center?

Sincerely hope I can get you help!

StatDave
SAS Super FREQ

The GEE model does not use random effects, so you cannot add a random effect for CENTER in your PROC GEE model. If observations are considered correlated within IDs and observations from different IDs are considered uncorrelated, then SUBJECT=ID is what you need. And you are already adjusting for CENTER by including it as an effect in the MODEL statement.

sas-innovate-2024.png

Available on demand!

Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.

 

Register now!

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
  • 2 replies
  • 369 views
  • 1 like
  • 2 in conversation