1
$\begingroup$

Quick question about the output of PROC SEQDESIGN. I was playing around with the O'Brien Fleming method trying to understand how we can interpret the results spit out by SAS for a mock study with survival outcome with the following specifications: randomized phase II trial where I'm trying to test treatment A vs treatment B (standard of care) and patients are randomized 1:1 to either treatment.

We have a 15 month accrual, rate of 10 patients per month, follow-up is 24 months, median PFS for B is 9 months, median PFS for A is expected to improve from 9 to 15 months. I want to design an interim analysis with OBF boundary, at 1-sided alpha for 90% power. I used the standard template from SAS PROC SEQDESIGN and I got the output below. My question is: what part of all the stuff below tells me whether we can reject the null hypothesis or not at each of the four stages? Is it the table with the Boundary Information where we look for when the alternative ref value is bigger than the upper boundary value (i.e. stage 3) and that's where we can stop the trial and reject Ho? Or how do I interpret all this output to draw a conclusion about how early we can stop the trial and decide whether treatment A is efficacious or not?

Also, why does the follow up time (circled in red in sample size summary) say 33.9 months and not 24? And then in last table, why is the N stuck at 150 starting with stage 2, what does that mean?

enter image description here

enter image description here

enter image description here enter image description here

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.