type known.designs() in PowerTOST [Study As­sess­ment]

posted by Helmut Homepage – Vienna, Austria, 2019-02-20 17:14 (1441 d 13:53 ago) – Posting: # 19941
Views: 8,933

Hi Rosy,

❝ But in this case: https://accp1.onlinelibrary.wiley.com/doi/abs/10.1177/009127009903901108?sid=nlm%3Apubmed


❝ The study had an open-label, single-dose, three-way crossover design. Subjects were randomly assigned to receive one of three treatments per period


Was it a Latin Square (ABC|BCA|CAB) or a Williams’s design (ABC|ACB|BAC|BCA|CAB|CBA)? Not mentioned anywhere in the paper. But this part is strange:

Seventeen healthy [:blahblah:] were enrolled.

Enrolled, how comes? It is OK to have dropouts but to start a study with incomplete sequences is bizarre. The sample size has to be a multiple of the number of sequences.

❝ A vs B ----> IC (84.9-106)

❝ A vs C ----> IC (169-211)

❝ B vs C ----> IC (178-222)


❝ 100*CVfromCI(lower=0.849, upper=1.06, n=17, design='2x2x3', alpha=0.05)

❝ it's that correct???


No, it isn’t. "2x2x3" is for the two-treatment two-sequence three-period full replicate design (TRT|RTR).
For the Latin Square use "3x3" and for the Williams’ design "3x6x3". BTW, in all functions of PowerTOST the default is alpha=0.05. As long as you deal with the 100(1–2×0.05) = 90% confidence interval you can simply leave it out. ;-)

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
22,477 posts in 4,708 threads, 1,603 registered users;
11 visitors (0 registered, 11 guests [including 6 identified bots]).
Forum time: 07:07 CET (Europe/Vienna)

I think it is much more interesting to live with uncertainty
than to live with answers that might be wrong.    Richard Feynman

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