Log in
Register|
libaiyi ★ China, 2018-06-28 13:47 (2488 d 04:49 ago) Posting: # 18988 Views: 4,555 |
|
|
Dear all, I want to know how to calculate the sample size when there exists R, T1, T2 under 3*3 or 6*3 design? Is there any software or R package available for statistical analysis of william design or 3*3 design when there exists R, T1, T2? Thanks in advance.  |
|
Helmut ★★★   Vienna, Austria, 2018-06-28 14:57 (2488 d 03:38 ago) @ libaiyi Posting: # 18989 Views: 3,974 |
|
|
Hi libaiyi, ❝ Is there any R package available for statistical analysis of william design or 3*3 design when there exists R, T1, T2? The function sampleN.TOST() of package PowerTOST. After installing/attaching in the R-console or the command window of R Studio type known.designs() to see what is covered. In sampleN.TOST() use the argument design (i.e., design="3x6x3" for the six-sequence Williams’ design or design="3x3" for the Latin Square).For low to moderate CVs sample sizes will be identical. — 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 |
|
d_labes ★★★ Berlin, Germany, 2018-06-28 15:30 (2488 d 03:05 ago) @ libaiyi Posting: # 18990 Views: 3,864 |
|
|
Dear libaiyi, additional to what Helmut has recommended: Calling sampleN.TOST() with argument design="3x6x3" is appropriate if you aim for analyzing the data according to the "all at once" strategy.If you analyze according to the "two at a time" strategy use design="2x2", the default for that argument.— Regards, Detlew |
Ing. Helmut Schütz