forget the partial replicate [Power / Sample Size]
Hi Niraj,
As John suggested go with PowerTOST. I would abandon the lousy partial replicate and opt for a fully replicated 3-period design (TRT|RTR) instead. If by any chance you are not allowed to scale (sWR <0.294), the partial replicate sometimes fails to converge in any (!) software. If that happens, you are in trouble. You have performed a study and are not able get a result (maybe
BTW, for HVDs/HVDPs I would never assume 90% < GMR <111% even if you saw such a GMR in the pilot. The GMR might jump around between studies. Don’t be overly optimistic.
❝ We have a data of partial replicate (TRR,RRT,RTR) pilot study and we have within-subject variability of reference formulation.
❝ Now suppose we want to estimate sample size for pivotal partial replicate (TRR,RRT,RTR) study using pilot study results.
As John suggested go with PowerTOST. I would abandon the lousy partial replicate and opt for a fully replicated 3-period design (TRT|RTR) instead. If by any chance you are not allowed to scale (sWR <0.294), the partial replicate sometimes fails to converge in any (!) software. If that happens, you are in trouble. You have performed a study and are not able get a result (maybe
TYPE=FA0(1) instead of TYPE=FA0(2) works – see this thread).BTW, for HVDs/HVDPs I would never assume 90% < GMR <111% even if you saw such a GMR in the pilot. The GMR might jump around between studies. Don’t be overly optimistic.
—
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 partial replicate - USFDA niraj.bhatt 2013-10-17 08:53
- sample size for partial replicate - USFDA jag009 2013-10-17 15:09
- sample size for partial replicate - USFDA niraj.bhatt 2013-10-18 08:18
- Table A3 Helmut 2013-10-18 13:51
- N=24 or N=27 d_labes 2013-10-18 14:34
- in praise of 100,000 sim’s Helmut 2013-10-18 15:02
- N=24 or N=27 niraj.bhatt 2013-10-19 06:19
- Table A3 niraj.bhatt 2013-10-19 06:18
- N=24 or N=27 d_labes 2013-10-18 14:34
- Table A3 Helmut 2013-10-18 13:51
- sample size for partial replicate - USFDA niraj.bhatt 2013-10-18 08:18
- forget the partial replicateHelmut 2013-10-18 00:14
- forget the partial replicate niraj.bhatt 2013-10-18 07:57
- PowerTOST and RSABE d_labes 2013-10-18 11:16
- Replicate Pilot study kumarnaidu 2014-04-11 07:37
- Replicate Pilot study ElMaestro 2014-04-11 10:27
- Replicate Pilot study kumarnaidu 2014-04-11 12:45
- Replicate Pilot study ElMaestro 2014-04-11 13:23
- Replicate Pilot study kumarnaidu 2014-04-14 06:22
- Replicate Pilot study ElMaestro 2014-04-11 13:23
- Replicate Pilot study kumarnaidu 2014-04-11 12:45
- Replicate Pilot study ElMaestro 2014-04-11 10:27
- forget the partial replicate niraj.bhatt 2013-10-18 07:57
- sample size for partial replicate - USFDA jag009 2013-10-17 15:09
