Adjusted Kaplan Meier Curve in counting process approach, and covariates are time varying

[haoduonge]

Hi all,

I need your help.

I want to have the adjusted Kaplan Meier by treatment group – a time varying covariate, adjusting for gender, race, crea, fib, alb.

Of the covariates: gender, race, and crea (continuous variable) are fixed variables, and fib (categorical variable) and alb (continuous variable) are time varying covariates.

For ‘crea’ I can get means by group, but I am not sure how to deal with alb as it is time varying covariate.

The link below has some guidance for doing it but it is all about fixed variables.

https://stats.idre.ucla.edu/sas/seminars/sas-survival/

I really appreciate any comments/guidance.

Hao

proc phreg data=TOTAL;

class treatment (ref='0') gender(ref='0') race(ref='0') FIB (ref='0');

model (start_final,stop_final)*outcome (0)= treatment gender race crea FIB alb/RL;

run;

ID	Treatment	outcome	start_final	stop_final	gender	race	crea	FIB	alb
1	0	0	0	1	0	999	0.98	2	4
1	0	0	1	2	0	999	0.98	1	3.7
1	0	0	2	3	0	999	0.98	999	3.7
1	0	0	3	3.617	0	999	0.98	2	3.8
1	1	0	3.617	4	0	999	0.98	2	3.8
1	1	0	4	5	0	999	0.98	2	3.8
1	1	0	5	6	0	999	0.98	2	3.8
1	1	0	6	6.245	0	999	0.98	2	3.8
2	0	0	0	1	0	0	0.9	2	3.6
2	0	0	1	2	0	0	0.9	1	4.3
2	0	0	2	3	0	0	0.9	0	4
2	0	0	3	3.047	0	0	0.9	0	4.4
3	0	0	0	1	0	3	0.98	2	4.1
3	0	0	1	2	0	3	0.98	2	4
3	0	0	2	3	0	3	0.98	2	4.1
3	0	0	3	4	0	3	0.98	2	4
3	0	0	4	5	0	3	0.98	1	4.2
3	0	0	5	6	0	3	0.98	1	4.9
3	0	1	6	6.486	0	3	0.98	1	4.6