Potvin & Montague not acceptable at all?! [Two-Stage / GS Designs]

posted by Helmut Homepage – Vienna, Austria, 2012-07-05 14:57 (3121 d 00:50 ago) – Posting: # 8893
Views: 17,945

Hi Shuanghe!

» » See also this thread […]
» The post is about method B or C. However, here the thing is bit different. What I forgot to mention is that after sending out synopsis based on method C one of the comments I got, apart from "not valid in Europe :blahblah:", is that "power does not count in order to make a decision. The decision can not depend on the results of the power."

Phantastic № 2! Of course post hoc power is irrelevant in BE, but obviously these guys (of the agency or – even worse – the BSWP) did|do not comprehend that the intermediate [sic] power estimation is part of the framework of Potvin et al. & Montague et al.

» I don't know how many ways we can interpret this phrase.

Stupidity? Especially “The decision can not depend on the results of the power.” WTF does the apodictic “can not” mean? OK, the framework showed that α is maintained. Of course this does not imply that skipping this step will not work at well. We just don’t have any evidence (i.e., a published reference).1 I don’t have the means to set up simulations but would be a rather interesting task.2 ElMaestro?

» Since Potvin's methods are all somehow based on power evaluation in its flowchart so may be this is the reason they say "not valid ..."?

Only in the intermediate step! Finally (i.e., after requests of the type “The applicant showed BE, but power was only 70%. Please justify.”) they have realized that post hoc power is irrelevant. But this is not an issue in this framework. See the last sentence in the description of Methods B–C:

Stop here whether BE is met or not and regardless of the power achieved.

(my emphasis)

» Anyway, this is the reason we changed synopsis to use another method without power evaluation as I mentioned.

Great. Quod licet Iovi, non licet bovi. Unless I have seen simulations showing otherwise I have to assume that the patient’s risk is not controlled.

» » Seems that some regulators believe sic in B, but then they should be happy with the even more strict method D as well. Or are they really thinking that α 0.0294 is a universal constant?
» If they don't like power evaluation in the flowchart, B and D should also be unacceptable to them.

According to what you said it seems so.3

» » Great. This is not even Method B (abandoning the power estimation step).
» Nope. We knew that and did it deliberately to avoid power evaluation.

I understand. α?

» » If the agency accepted your method without an intermediate power estimation they should ask themselves which risk to patients they are actually accepting.
» Don't know if there's some kind of pact here (this is a BE for certain SUPAC […]). We were warned that the agency accept this study only in this specific country. It implied that the design might not be valid in other EU countries.
» » For example, using 94.12% confidence intervals for both the analysis of stage 1 and the combined data from stage 1 and stage 2 would be acceptable, …
» » That’s Method B!
» My understanding is different. B involve power evaluation as well (After BE failed in stage 1, there's a step of evaluation power to determine if it should be stopped (Pt>= 80%) or continue (Pt<80%). What I understood from the guideline is that no power evaluation is involved in this example.

I meant that this is Method B, because 94.12% CIs are mentioned for both stages. In Method A 94.12% CIs are only applicable if power in step 1 <80%.

» » Enjoyed especially the talks outside in the smoker’s Ghetto. :smoke:
» It's a surprise that we actually talked about BE until 2 or 3 AM :-D :clap:.

3 a.m. is not particular for me, but you and some other guys showed a lot of stamina!

  1. Appeal to ignorance—the claim that whatever has not been proved false must be true, and vice versa (e.g., There is no compelling evidence that UFOs are not visiting the Earth; therefore UFOs exist—and there is intelligent life elsewhere in the Universe. Or: There may be seventy kazillion other worlds, but not one is known to have the moral advancement of the Earth, so we’re still central to the Universe.) This impatience with ambiguity can be criticized in the phrase: absence of evidence is not evidence of absence.
    Carl Sagan
    The Demon-Haunted World: Science as a Candle in the Dark
    Ballantine, New York, p213 (1st ed. 1997)
    (my emphasis)
  2. Edit: In the meantime I can do better. See this post.
  3. Edit: End of July I saw a couple of deficiency letters. Some countries would accept Potvin B/C and Montague D if their applicability is justified for the particular study (aka a posteriori simulations) whilst others are not willing to accept intermediate power estimations at all! :angry:

Dif-tor heh smusma 🖖
Helmut Schütz

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes

Complete thread:

 Admin contact
21,308 posts in 4,444 threads, 1,489 registered users;
online 11 (2 registered, 9 guests [including 2 identified bots]).
Forum time: Wednesday 14:47 CET (Europe/Vienna)

Power: That which is wielded by the priesthood of
clinical trials, the statisticians, and a stick which they use
to beta their colleagues.    Stephen Senn

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz