Some testing (Part II) [Power / Sample Size]
Continuing…
FDA, 3-period, 80% power
FDA, 3-period, 90% power
FDA, 4-period, 80% power
FDA, 4-period, 90% power
I will ask them whether they have used 0.89 like in their paper from 2009 instead of log(1.25)/0.25 ≈ 0.8925742…
I like the option to specify unequal CVs of test and reference as
It will pay off to have a ‘better’ formulation.
FDA, 3-period, 80% power
0.85 0.90 0.95 1.00 1.05 1.10 1.15 1.20
PT TE PT TE PT TE PT TE PT TE PT TE PT TE PT TE
0.30 144 145 45 45 24 24 21 21 24 24 39 39 81 82 306 >201
0.35 69 74 36 37 24 24 21 22 24 25 33 34 51 54 105 109
0.40 60 60 33 33 24 24 21 22 24 24 30 31 42 47 99 104
0.45 60 59 30 31 24 23 21 22 24 24 27 29 42 43 120 116
0.50 66 66 30 30 24 24 21 22 24 23 27 28 42 41 144 133
0.55 78 80 30 30 24 24 24 22 24 24 27 28 45 44 171 172
0.60 90 88 30 31 24 24 24 23 24 24 30 30 48 50 198 >201
0.65 102 98 33 32 27 25 24 24 24 25 30 31 57 53 228 >201
0.70 117 106 36 35 27 26 24 25 27 26 33 31 63 62 258 >201
0.75 132 136 39 38 27 27 27 26 27 27 36 34 69 70 288 >201
0.80 144 144 42 40 30 29 27 27 30 29 39 37 78 76 318 >201
FDA, 3-period, 90% power
0.85 0.90 0.95 1.00 1.05 1.10 1.15 1.20
PT TE PT TE PT TE PT TE PT TE PT TE PT TE PT TE
0.30 228 >201 66 65 33 33 27 26 33 32 57 55 123 122 495 >201
0.35 102 106 48 51 33 32 27 28 33 32 45 47 72 77 177 186
0.40 102 99 45 45 30 31 27 28 30 31 39 43 63 68 222 >201
0.45 126 128 42 43 30 30 27 28 30 30 39 40 69 69 273 >201
0.50 150 158 45 45 30 31 27 28 30 30 39 40 81 79 333 >201
0.55 177 178 48 50 33 31 30 28 30 31 45 42 96 96 393 >201
0.60 207 199 57 54 33 33 30 30 33 34 48 50 111 112 456 >201
0.65 237 >201 63 61 36 35 33 32 36 36 54 53 126 125 522 >201
0.70 270 >201 72 68 39 39 36 34 39 37 63 61 144 141 594 >201
0.75 300 >201 81 80 45 43 39 37 42 41 69 68 159 161 660 >201
0.80 333 >201 90 83 48 48 42 41 48 47 75 75 177 176 732 >201
FDA, 4-period, 80% power
0.85 0.90 0.95 1.00 1.05 1.10 1.15 1.20
PT TE PT TE PT TE PT TE PT TE PT TE PT TE PT TE
0.30 96 96 30 30 18 17 14 15 16 17 26 27 54 55 206 200
0.35 50 54 26 26 18 18 16 16 18 18 24 24 36 39 76 79
0.40 42 43 22 24 18 18 16 16 16 17 22 22 32 33 68 72
0.45 42 44 22 23 16 18 16 16 16 17 20 21 30 32 80 82
0.50 46 45 22 22 18 17 16 17 16 17 20 21 30 31 96 99
0.55 52 52 22 22 18 18 16 17 18 17 20 21 32 31 114 116
0.60 60 58 22 23 18 18 16 17 18 18 20 21 34 34 132 124
0.65 68 74 24 24 18 19 18 18 18 18 22 22 38 36 152 155
0.70 78 75 24 24 18 19 18 18 18 19 22 23 42 44 170 167
0.75 88 81 26 26 20 20 18 19 20 20 24 24 46 47 190 186
0.80 98 95 28 29 20 21 20 20 20 20 26 25 52 51 210 >201
FDA, 4-period, 90% power
0.85 0.90 0.95 1.00 1.05 1.10 1.15 1.20
PT TE PT TE PT TE PT TE PT TE PT TE PT TE PT TE
0.30 152 152 44 44 22 23 18 18 22 22 38 38 82 81 332 >201
0.35 76 80 36 38 22 23 20 20 22 23 32 34 52 55 126 128
0.40 70 70 32 32 22 22 20 20 22 22 28 30 46 48 148 158
0.45 84 84 30 32 22 22 20 20 22 22 28 30 48 49 184 181
0.50 100 102 32 32 22 23 20 20 22 22 28 30 54 54 220 >201
0.55 118 123 34 34 22 23 20 21 22 22 30 31 64 61 262 >201
0.60 138 139 38 38 24 24 22 22 24 24 34 33 74 71 304 >201
0.65 160 159 42 44 26 26 22 23 24 25 36 35 84 81 348 >201
0.70 180 172 48 46 28 26 24 24 26 27 42 43 96 97 394 >201
0.75 200 195 54 53 30 29 26 26 30 29 46 48 106 106 442 >201
0.80 222 >201 60 60 32 33 28 28 32 31 52 51 118 113 488 >201
I will ask them whether they have used 0.89 like in their paper from 2009 instead of log(1.25)/0.25 ≈ 0.8925742…
I like the option to specify unequal CVs of test and reference as
CV=c(T,R)
. Example for EMA, 3-period, T/R 0.95, 80% power (pooled CVintra 0.3 in all cases): CVWT CVWR n
0.2500 0.3458 24
0.3000 0.3000 27
0.3458 0.2500 30
It will pay off to have a ‘better’ formulation.
—
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
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
Complete thread:
- Sample size for RSABE Anu 2013-02-01 07:01
- Sample size for RSABE d_labes 2013-02-01 09:46
- Sample size for RSABE Anu 2013-02-07 06:58
- No analytic solution! Helmut 2013-02-07 12:32
- Coming soon ... d_labes 2013-02-08 11:57
- Wow! Helmut 2013-02-08 12:19
- Wow! Anu 2013-02-09 09:20
- read… Helmut 2013-02-09 09:35
- Bigamist d_labes 2013-02-09 18:11
- Some testing (Part I) Helmut 2013-02-10 18:35
- Some testing (Part II)Helmut 2013-02-11 01:00
- Power testing d_labes 2013-02-11 12:03
- the unknown x Helmut 2013-02-11 14:40
- Unequal CVs d_labes 2013-02-15 08:47
- Typo Helmut 2013-02-15 13:01
- Power testing d_labes 2013-02-11 12:03
- Wow! Anu 2013-02-09 09:20
- Wow! Helmut 2013-02-08 12:19
- Coming soon ... d_labes 2013-02-08 11:57
- No analytic solution! Helmut 2013-02-07 12:32
- Sample size for RSABE Anu 2013-02-07 06:58
- Sample size for RSABE d_labes 2013-02-01 09:46