0
$\begingroup$

I have been reading up on group sequential clinical trial designs and came across the concept of non-binding futility boundaries. Intuitively, it makes sense to me that continuing the trial after crossing a binding futility boundary would increase your chances of a Type-I error--hence, the need to develop methods for a non-binding boundary.

But there seems to be no discussion/mention of non-binding efficacy boundaries. It makes sense that continuing after crossing the efficacy boundary wouldn't affect Type-I error but it would increase Type-II error (and thus, decrease power). The fact that this is not discussed anywhere makes me think that I'm missing something obvious/there's a glaring gap in my knowledge. I would appreciate some insight into this.

$\endgroup$

1 Answer 1

0
$\begingroup$

Actually, I do not think that you are missing something out, I'd rather assume that people like us (probably not having been employed in industry or at least not for too long) are "lacking" industry perspective. Consider having an non-binding efficacy, this would provide the possibility for not-claiming study success also the data indicates to do so. I really don't think that this would be something someone in practice would ever choose to do (as it would potentially lead to intentional waiver of money) which might in turn be the reason that there is no publication about such concept at all.

$\endgroup$
2
  • $\begingroup$ Besides that, what you wrote is obviously right. Establishing such boundaries wouldn't affect type I error rate (no error can be committed without concluding with rejection), but there'd clearly be a power decrease (T2E increase) since intentionally missing out a rejection opportunity. Shouldn't be too hard to properly write that done and/or proof by simulation! $\endgroup$ Nov 3, 2021 at 21:25
  • $\begingroup$ I basically came to the same conclusion as you. There's no real incentive to continue once you have crossed the efficacy boundary. But practically speaking, sponsors are much more likely to continue trials after crossing the futility boundary. For any future readers, I found this thesis to be a good reference for the practical side of things. See p. 70. $\endgroup$ Nov 4, 2021 at 22:28

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.