I am new to SAS and running into a road block concerning Cumulative Incidence. In a nutshell I have a data set for cancer patient that recived trasplant. We are looking for engraftment data but need to control for those that failed to engraft by a certain day due to death. The data set I am using is censored on the following:
Fields being used are:
ANC500 (Days from Transplant to Engraftment)
ANC_Censor (Did they Engraft)
CensDth (Did they Die)
Cens_ANC28 (Did they die by day28)
ANC_Censor (1=Yes 0=No)
On those that did not engraft (0):
Dead Yes = 1
Dead No = 0
On those that are Dead (1)
Death LTE 28 Days = 1
Death GT 28 Days = 0
I am trying to use Phreg but not sure what to put after the = sign in:
Model anc500*Cens_ANC500(0) = ??
The time on this is days from Transplant to Engraftment, and I need to censor on those that did not engraft by 28 days becasue they died in that time period.
I hope that makes sense. Help is GREATLY appreciated.
With PHREG, the first variable is the days until something happened. The second variable is whether what happened was a censoring event or a real event. So your ANC500 needs to be restructured to combine the dates to engraftment with days to death and days to last follow-up (or declaration of failure to engraft). Then your Cens_ANC500 can have multiple codes representing the different conditions at the end.
Because you have (at least) three endpoints, you have a competing risks situation and need to either do a multiple event model or a sensitivity analysis (combining different event types).
It may be conceptually easier to reframe your model to have the outcome of interest being "failure to engraft" and then you just censor on engraftment. Censoring on death often leads to a "waiting time bias" that needs to be carefully evaluated (See the article by Mitch Gail about the Stanford Heart Transplant data (Annals of Internal medicine, 1972) for the classic example.).
On the right of the = go the candidate explanatory variables, age, sex, etc.