Bioequivalence and Bioavailability Forum

Hi Osama,

❝ I can't find anything in this draft indicates removing of subjects add on Design, like the EMA (May 2012)?

Are you referring to the Q&A-document?

❝ … has the WHO decided to keep it also valid?

I don’t think so (cannot find Add-ons anywhere in the draft). Annex 7 to WHO’s TRS № 937 (2006) mentioned Add-ons in Section 6.3.2. At the end of the section it was stated:

Add-on designs must be carried out strictly according to the study protocol and SOPs, and must be given appropriate statistical treatment.

(my emphasis)
In the past Australia’s TGA and more recently Health Canada accepted Add-ons – if a Bonferroni-correction (i.e., α 0.025 → 95% CI) was applied. In the meantime both agencies dropped Add-ons.

❝ I thought the reason of establishing the two-stage sequential designs is as they give better control of patient's risk than the add on design.

Exactly. See also this post and followings. Based on statistical theory I would say that a Bon­fer­roni-correction should maintain the patient’s risk ≤0.05 in any TSD (and Add-ons as well). Note that Bonferroni’s adjusted α of 0.025 is smaller than any α of the published TSD-methods. Though this would lead to a con­servative patient’s risk, the sample size penalty will be larger than necessary – which is not desirable both from ethical and economical perspectives.