Bioequivalence and Bioavailability Forum

Hi ElMeaestro,

❝ According to my psychic tasseographer, WHO's assessors are those who write the WHO guideline and they are to a large extent the same as the guys who are writing the EMA's guideline.

Supported.

❝ ❝ In order to employ a two-stage design, adjustments must be made to protect the overall Type I error rate and maintain it at 5%. In order to do this both the interim and final analy­ses must be con­ducted at adjusted levels of signi­fi­cance, with the confidence intervals calculated using the adjusted values.

❝

❝ I think the quoted exerpt above in actuality means that an applicant must pick both alphas so as to have the type I error controlled at 5%.

Agree.

❝ I agree that in the strictest sense one could read it in such a way that they require an adjusted alpha after stage one (i.e. not 0.05) but I do not think this is what they strictly mean and I do not think this is what they will endeavour to enforce.

Do you remember the cases leading to deficiency letters by European regulators if studies were performed according to Method C? For a particularly nasty example see here. AUC passed in the first stage (Method C – according to the protocol; unadjusted α since power >80%) but failed in the post-hoc switch to Method B. If the sponsor would have known beforehand that Method C is not acceptable, they would have initiated a – rather small – second stage and likely would have passed with all glory.

❝ So I think there's still hope for Potvin C.

❝ If you wish you can try Potvin C at alpha₁=0.049 or 0.000083 or whatever and find a good correspond level of alpha₂ for an overall alpha of 0.05.

Correct. Nevertheless not everybody has the guts to perform own simulations, though Power2Stage is such a nice tool.

BTW, below type I errors (blue=low, red=high) for Methods B/C and a conventional fixed sample design (abscissa n₁ 12–60, ordinate CV 10–100%).

Bonus question: Which one (B or C) mimics the fixed sample design better?