Bioequivalence and Bioavailability Forum • Group sequential designs

d_labes
★★★

Berlin, Germany,
2014-02-07 16:43
(4520 d 09:48 ago)

Posting: # 12367
Views: 2,606

Group sequential designs – Canada [Regulatives / Guidelines]

Dear All!

Questions over questions.

The Canada guidance "Conduct and Analysis of Comparative Bioavailability Studies" mentions in paragraph "2.3.2 Alternate Study Designs" the Group Sequential Designs. These designs are amongst others characterized by predefined numbers of subjects in the stages (recommended 2 stages only).

Further it is written: "… Usually the strategy with this design is to accept bioequivalence at the first stage and only go to the second stage when the intra-subject variance from the first stage is very large."

That sounds to me like a negated futility criterion. Than it should read "to accept or reject bioequivalence at the first stage", I think. Anybody out there to shed some light on this? Does anybody know what is meant with "very large"? Is there an example anywhere?

Another sentence makes me also headache: "This method precludes the need for a stage effect in the model." Why this?

—
Regards,

Detlew

ElMaestro
★★★

Denmark,
2014-02-07 17:15
(4520 d 09:16 ago)

@ d_labes
Posting: # 12368
Views: 2,066

Group sequential designs – Canada

Post reply

Hi Detleffff,

❝ (blah blah blah)

❝ Further it is written: "… Usually the strategy with this design is to accept bioequivalence at the first stage and only go to the second stage when the intra-subject variance from the first stage is very large."

❝ That sounds to me like a negated futility criterion. Than it should read "to accept or reject bioequivalence at the first stage", I think. Anybody out there to shed some light on this? Does anybody know what is meant with "very large"? Is there an example anywhere?

I think not, at least not when we talk public domain. I believe HC's interpretation of the term "usually" means "without any precedence whatsoever". The term occurs several more times elsewhere in the document where it has a found a use that makes a bit more sense to me.

❝ Another sentence makes me also headache: "This method precludes the need for a stage effect in the model." Why this?

No idea.

I must admit that to me, the whole section 2.3.2.1. doesn't live any real life. It's the Potvin way or the highway.

Finally, check out the answer to question 9 here. You must give the agency some style points for creativity in their solutions to number-crunching issues. Perhaps the two documents are written by one and the same person?

—
Pass or fail!
ElMaestro