topic Re: How to generate cumulative mean function by considering competing events in SAS Programming

How to generate cumulative mean function by considering competing events

SeaMoon_168 — Mon, 19 Aug 2024 03:17:17 GMT

The original code can be accessed from SAS: Analysis of Multivariate Failure Time Data

https://documentation.sas.com/doc/en/statug/15.2/statug_phreg_details45.htm#statug_phreg012597

proc phreg covs(aggregate);
   model (Tstart,Tstop)*Status(0)=Trt Age;
   baseline covariates=Pattern out=out2 cmf=_all_;
   id ID;
run;

However, if I add eventcode=1, the code does not work.

proc phreg covs(aggregate);
   model (Tstart,Tstop)*Status(0)=Trt Age/ evencode=1;
   baseline covariates=Pattern out=out2 cmf=_all_;
   id ID;
run;

Can anyone help me figure it out? Many thanks!

Re: How to generate cumulative mean function by considering competing events

ballardw — Mon, 19 Aug 2024 16:27:45 GMT

Doesn't work is awful vague.

Are there errors in the log?: Post the code and log in a code box opened with the "</>" to maintain formatting of error messages.

No output? Post any log in a code box.

Unexpected output? Provide input data in the form of data step code pasted into a code box, the actual results and the expected results. Instructions here: https://communities.sas.com/t5/SAS-Communities-Library/How-to-create-a-data-step-version-of-your-data-AKA-generate/ta-p/258712 will show how to turn an existing SAS data set into data step code that can be pasted into a forum code box using the "</>" icon or attached as text to show exactly what you have and that we can test code against.

Assuming of course your submitted code was EVENTCODE=1 not the EVENCODE shown in your post.

Quite often the LOG does have related information that you should share.

Re: How to generate cumulative mean function by considering competing events

SeaMoon_168 — Mon, 19 Aug 2024 17:17:48 GMT

data is

ID	TStart	TStop	Status	Trt	Age
174054	0	293	0	1	38
204001	0	219	1	2	12
204001	219	373	2	2	12
204001	373	414	0	2	12

I am sorry for the typo, It should be eventcode=1.

Actually I got some warnings. It seems cmf cannot work with Fine and Gray competing risk analysis together? So how can I write the code to generate mcf and competing risk together?

Re: How to generate cumulative mean function by considering competing events

Ksharp — Tue, 20 Aug 2024 08:21:34 GMT

1)
I think you need to change your data structure(a subject has only one obs/Time/Status) to use EVENTCODE=1.
You can " create a time-varying covariate using programming statements in proc phreg." other than this kind of data structure [TStart, TStop] .
And Here is an example:
(here 'in_hosp' is a time-varying covariate)
proc phreg covs(aggregate);
model Time*Status(0)=Trt Age in_hosp/ evencode=1;
if Time> 219 then in_hosp = 0;
else in_hosp = 1;
run;

2)
If you don't have time-varying covariates, that would be better to use this code:
(Make sure a subject has only an obs and a TIME value and a STATUS value)
proc phreg covs(aggregate);
model Time*Status(0)=Trt Age/ evencode=1;