topic Re: Competing risk graph question in Statistical Procedures

Competing risk graph question

rsubrama — Tue, 14 Jun 2016 06:55:56 GMT

I am trying to perform competing risk analysis for outcomes using a patient cohort data on SAS studio release 9.04. I checked codes on line and found that we could use proc phreg or %macro cuminc. I am planning on using proc phreg using these codes on sas support site

ods graphics on;
proc phreg data=Bmt plots(overlay=stratum)=cif;
   class Disease (order=internal ref=first);
   model T*Status(0)=Disease / eventcode=1;
   Hazardratio 'Pairwise' Disease / diff=pairwise;
   baseline covariates=Risk out=out1 cif=_all_ / seed=191;
run;

My question is how do I code so that the graph shows all outcome status. This code only plots for the outcome of interest (eventcode =1). Thanks

Re: Competing risk graph question

JacobSimonsen — Wed, 22 Jun 2016 11:08:11 GMT

You can not calculate all the survival curves in only one run of phreg. You can of course run phreg for each outcome. The Fine and Gray method which proc phreg use only take account for one outcome at a time.

I am not sure that if you run phreg for each outcome that the total sum will add up to one (exactly).
If you like, I can give you a macro which calculate all curves in one time using the Aalen Johansen estimator.

Re: Competing risk graph question

rsubrama — Wed, 22 Jun 2016 18:49:47 GMT

What you say is accurate - I tried to do individual phregs and it did not add up to one. Others suggested individual KM for each outcome, which will work but is obviously univariate. I would appreciate if you can send me your macro. Thanks.

Re: Competing risk graph question

JacobSimonsen — Thu, 23 Jun 2016 06:49:22 GMT

Here you have the program that calculate Aalen Johansen estimates. It was not written as a macro, so bit editing will perhaps be neccessary. I hope you find it useful.