PROC PHREG: hazard ratio when interaction term is added

[_MooMoo]

Hello SAS communities! 

Suppose I would like to fit 

where X1 and X2 are dichotomous variables.

Below code will give me HR of X1 at each level of X2 due to interaction term.

proc phreg data=demo;

   class X1 X2 / param=ref;

   model (start, stop) * Y(0)=X1 X2 X1*X2;

   hazardratio X1/diff=ref;

However, I am trying to output overall effect of X1. In other words, I would like to say - Y increased/decreased by __% when X1=1 comparing to X1=0 after accounting for other covariates in the model.

In that case, will below code output the number I need to make above statment? LSMEANS only work under param=glm... will this different from when setting param=ref?

proc phreg data=demo;

   class X1 X2 / param=glm;

   model (start, stop) * Y(0)=X1 X2 X1*X2;

   lsmeas X1/cl;

Thank you! If you have other suggestions, I appreciate that too!

[pink_poodle · Accepted solution]

Yes, but you need to to explicitly state that your reference term is X1, like so:
class x1 x2 / param=glm ref=x1;
For more information about class and param, please see:
https://documentation.sas.com/?docsetId=statug&docsetVersion=15.1&docsetTarget=statug_phreg_syntax06...

[_MooMoo]

Thank you for the suggestion! 

However, when I add ref=X1 statement after param=glm, it gives an error like below.

ERROR 22-322: Syntax error, expecting one of the following: FIRST, LAST.
ERROR 76-322: Syntax error, statement will be ignored.

[pink_poodle]

This is because it has to be a level: REF=’level’, sorry, not X1. Like if your variable has levels 0 and 1, and you want to compare to 1, then it would be REF='1'.

[_MooMoo]

Aha! That's it.