Bioequivalence and Bioavailability Forum

adjusted alpha = 0.038 [Two-Stage / GS Designs]

posted by Helmut  – Vienna, Austria, 2012-08-03 16:26 (5076 d 20:42 ago) – Posting: # 9032
Views: 17,606

Dear Detlew!

❝ Where did the α_adj.=0.045 came from? Luckily guess? Or some Hermetism?

More an educated guess. With n₁ 12 and CV 10% a study is already large enough (fixed sample design 98.8% power) and chances to require a second stage are very low. Since Methods C/D allow for stopping in stage 1 with a 90% CI in these methods α_emp. ~ α_nominal. In Method B we have to pay the penalty and α_emp. ~ α_adj.. That’s even more pronounced for higher n₁ and the same CV (where <0.1% of studies reach stage 2). So why not increase the level of α_adj.? 0.045 was a quick-shot – maybe one can even go to close <0.05.

I will try a more realistic example (n₁ 36, CV 30%; fixed design power 77.2% and 81.6% for n 40). With α_adj. 0.0294 Potvin got α_emp.: 0.0397 (B) and 0.0477 (C); studies in stage 2: 29.0% (B) and 22.7% (C).
10⁶ sims of Method B with α_adj. 0.0380 (= quick-shot obtained from 10⁴ sims) are running…
BTW, where do you think Method B’s 0.0280 came from?

—
Dif-tor heh smusma 🖖🏼 Довге життя Україна! 
Helmut Schütz


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

Complete thread:

• two-stage design power 90% second stage Yvonne 2012-08-02 09:50 [Two-Stage / GS Designs] 
  • two-stage design power 90% second stage ElMaestro 2012-08-02 10:17
    • two-stage design power 90% second stage Yvonne 2012-08-02 11:47
      • two-stage design power 90% second stage ElMaestro 2012-08-02 11:54
  • two-stage design power 90% in sample size adaption d_labes 2012-08-02 10:33
    • two-stage design power 90% in sample size adaption ElMaestro 2012-08-02 11:29
      • two-stage design power 90% in sample size adaption Yvonne 2012-08-02 12:06
        • two-stage design power 90% in sample size adaption ElMaestro 2012-08-02 16:59
  • Are simulations sufficient? …lenghty post! Helmut 2012-08-02 17:39
    • adjusted alpha = 0.045 d_labes 2012-08-03 11:33
      • adjusted alpha = 0.038Helmut 2012-08-03 14:26
        • adjusted alpha by sims? d_labes 2012-08-03 15:48
          • Yeah but, no but, yeah but, no but… Helmut 2012-08-03 16:39
            • Yeah but, no but ... d_labes 2012-08-07 14:42
              • Yeah but, no but ... Helmut 2012-08-07 15:14