topic Re: Stratified Cox PH model: time-stratification in SAS Programming

Stratified Cox PH model: time-stratification

_MooMoo — Wed, 16 Sep 2020 21:30:51 GMT

Hello,

I am wrapping my head around to figure out how to model stratified cox ph model.

Assuming baseline hazard change over time, I partitioned follow-up time into two time intervals. 1 time interval for early to mid period and another time interval for late period. For example, let's say a person was followed 10 years, which can be represented as (0,10). I partitioned this time interval into two pieces such as (0, 8 ) falls into first stratum (time_strata=1) and (8,10) falls into second stratum (time_strata=2).

Suppose the main covariate I am interested in is X1 and partition data set is data set I partitioned the follow-up time into two time-intervals from original data set. I coded SAS as below...

proc phreg=partition;

class X1;

model Y=X1;

strata time_strata;

run;

The code above gives me the exact same output as below code...

proc phreg=original;

class X1;

model Y=X1;

run;

Why is this happening? Can I perform stratified analysis in this way (having time interval as strata)? If not, any other suggestions are appreciated.

Thanks in advance!

Re: Stratified Cox PH model: time-stratification

pink_poodle — Fri, 18 Sep 2020 23:44:07 GMT

Does it give you the Summary of the Stratum Levels table in case when you have the strata statement?

Re: Stratified Cox PH model: time-stratification

_MooMoo — Tue, 22 Sep 2020 01:57:06 GMT

As I more think about this, I think the approach I explained above is wrong. Since time dependency of risk getting main outcome is already absorbed in the baseline hazard rate even though I did not stratify by time interval, there is no point running stratified cox regression where stratification level is time interval.