Hazard ratio for different groups with PHREG

Lulu09 — Mon, 10 May 2021 02:01:12 GMT

There are 3 groups. And I want to get the hazard ratio for group 1 vs group 3, and group 2 vs group 3. The results that are generated from below 2 methods are not the same. So should I better put all 3 groups into PHREG, and set group 3 as reference level, Or should I select 2 groups each time when I execute PHREG procedure ? Thank you very much.

Method 1:

proc phreg data = xx alpha=0.05;
class trt (ref="3");
model aval*cnsr(1)=trt /ties=exact;
hazardratio trt / diff=all;
run;

Method 2:

proc phreg data = xx(where=(trt in (1,3) )) alpha=0.05;
class trt (ref="3");
model aval*cnsr(1)=trt /ties=exact;
hazardratio trt ;
run;

proc phreg data = xx(where=(trt in (2,3) )) alpha=0.05;
class trt (ref="3");
model aval*cnsr(1)=trt /ties=exact;
hazardratio trt ;
run;

Re: Hazard ratio for different groups with PHREG

OsoGris — Mon, 10 May 2021 08:52:20 GMT

I think it is advisable to keep all three treatments in one model. If you want the differences with the reference category you can use the option DIFF=REF on the HAZARDRATIO statement.

topic Hazard ratio for different groups with PHREG in Statistical Procedures

Hazard ratio for different groups with PHREG

Re: Hazard ratio for different groups with PHREG