05-13-2018 02:56 PM
I have a question. I know people can use multiple comparisons such as Hsu's MCB to find out among several groups, which pair of group have the biggest contrast of the treatment mean, and which groups do not differ in their means of treatment effects.
Now I have a data for survival analysis in which there are several groups, I want to compare their survival risk curve in the observation time to see which groups do not differ and which group different using MCB. Is that possible? I know using Kaplan-Meier curve we can only compare each two groups to see if they differ in survival risk. But I hope to have something like Hsu's MCB so that I can lump those groups that do not differ in their survival risk together into one group.
05-14-2018 01:32 PM
I used adjust= statement
This is my code
proc lifetest data = roads.tepfulldata plots=survival(atrisk);
strata prior_group/test=logrank adjust=sidak;
But this code give me an output in which every 2 of the 16 categories of "prior_group' variable--a categorical variable with 16 values.
So generally this code can only help me figure out of every two groups are different from each other, but not the info about if the survival risk of multiple groups DO NOT differ thus be lumped together as one group.