Molins et al. (2017) [RSABE / ABEL]

posted by Helmut Homepage – Vienna, Austria, 2024-11-08 15:34 (147 d 01:50 ago) – Posting: # 24265
Views: 1,974

Hi Antigoni,

❝ Many thanks dear Helmut!

Welcome.
See also the function sample.size.adj() in this article. It implements our method1,2 and a more conservative one.3,4
Of course, such a conservatism comes with a price. The sample sizes can be prohibitively large.

                 method CVwT CVwR Target power Sample size Achieved power
             EMA (2010)  0.4  0.4          0.9          42        0.90325
Labes and Schütz (2016)  0.4  0.4          0.9          44        0.90523
   Molins et al. (2017)  0.4  0.4          0.9          78        0.90246
                 method   alpha     TIE
             EMA (2010) 0.05000 0.05572
Labes and Schütz (2016) 0.04326 0.05000
   Molins et al. (2017) 0.03061 0.05000



  1. Labes D, Schütz H. Inflation of Type I Error in the Evaluation of Scaled Average Bioequivalence, and a Method for its Control. Pharm Res. 2016: 33(11); 2805–14. doi:10.1007/s11095-016-2006-1.
  2. Assuming that the observed \(\small{CV_\text{wR}=}\) the true \(\small{CV_\text{wR}}\).
  3. Molins E, Cobo E, Ocaña J. Two-Stage Designs Versus European Scaled Average Designs in Bioequivalence Stud­ies for Highly Variable Drugs: Which to Choose? Stat Med. 2017; 36(30): 4777–88. doi:10.1002/sim.7452.
  4. Assuming the ‘worst case’ \(\small{CV_\text{wR}=30\%}\) – irrespective of the observed \(\small{CV_\text{wR}}\) because the maximum inflation of the Type I Error is always at the switching \(\small{CV_\text{wR}=30\%}\) regardless the design and sample size.

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz
[image]

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

Complete thread:

UA Flag
Activity
 Admin contact
23,413 posts in 4,924 threads, 1,668 registered users;
72 visitors (0 registered, 72 guests [including 6 identified bots]).
Forum time: 18:25 CEST (Europe/Vienna)

Nothing shows a lack of mathematical education more
than an overly precise calculation.    Carl Friedrich Gauß

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5