Log in
Register|
Ravi ★ India, 2008-11-20 13:57 (6426 d 04:28 ago) Posting: # 2749 Views: 6,198 |
|
|
Dear All, Can we predict Sample size for 2 x 2 crossover fasted study on the basis of estimates from a 3 x 3 crossover design in which Ref. is given as fasted and test product is given as both in fed and fasted. If yes please tell me the prodecure or formule to be used. — Thanks & Regards Ravi Pandey |
|
Helmut ★★★   Vienna, Austria, 2008-11-20 21:52 (6425 d 20:33 ago) @ Ravi Posting: # 2754 Views: 5,353 |
|
|
Dear Ravi! ❝ Can we predict Sample size for 2 x 2 crossover fasted study on the basis ❝ of estimates from a 3 x 3 crossover design [...] Yes and no. To quote Jaime in this post: 'Obviously 3x3 studies don't die out - but why?' 3x3 designs are flawed, see this post for details. ❝ If yes please tell me the prodecure or formule to be used. From a study in a 6×3 Williams' design you may calculate CVintra in the usual way as sqrt(exp(MSE)-1) and use it in sample size estimation for the 2×2 study. You may apply the same formula to a 3×3 study as well, but I don't have the slightest idea whether the result is unbiased. — Dif-tor heh smusma 🖖🏼 Довге життя Україна! ![[image]](https://static.bebac.at/pics/Blue_and_yellow_ribbon_UA.png) Helmut Schütz ![[image]](https://static.bebac.at/img/CC by.png) The quality of responses received is directly proportional to the quality of the question asked. 🚮 Science Quotes |
Ing. Helmut Schütz