Log in
RegisterTough job [Two-Stage / GS Designs]
Hi Helmut!
Thanks for the graph!
I actually tried both the 10^4 and 10^5 # of simulations (for about 5 different scenarios), the results are almost identical. I realized that 10^6 is a must when you go for Potvin’s 2-stage.
Methods C/D.
But if any of your sample CVs exceeds 30%, the acceptance limits are widened. They are no longer fixed at 0.8 and 1.25. When you enter your simulation with a starting CV of say 35%, most of your random samples will have an acceptance limit in the neighborhood of [0.7723, 1.2948]. In this case, when you still center it on ln(0.8), the simulated “type I error” will be huge.
Thanks for the graph!
❝ Yes, but as I said at the end of my post not only the grid is too coarse, but IMHO 104 sim’s are not enough.
I actually tried both the 10^4 and 10^5 # of simulations (for about 5 different scenarios), the results are almost identical. I realized that 10^6 is a must when you go for Potvin’s 2-stage.
❝ Which one of Potvin’s methods are you aiming at?
Methods C/D.
❝ Doesn’t make sense. ln(0.8)/ln(1.25) are fixed margins and we are testing for no inflation there. 0.748 is outside the margin and the GMR-restriction would reject all studies.
But if any of your sample CVs exceeds 30%, the acceptance limits are widened. They are no longer fixed at 0.8 and 1.25. When you enter your simulation with a starting CV of say 35%, most of your random samples will have an acceptance limit in the neighborhood of [0.7723, 1.2948]. In this case, when you still center it on ln(0.8), the simulated “type I error” will be huge.
Complete thread:
- Potvin’s 2-stage adaptive design GSD 2012-08-17 20:56
![[Mix]](https://static.bebac.at/img/mix.png "open in Mix view")
- Potvin’s 2-stage adaptive design + RSABE/ABEL Helmut 2012-08-18 00:39
- Potvin’s 2-stage adaptive design + RSABE/ABEL GSD 2012-08-31 16:30
- Tough job Helmut 2012-08-31 18:37
- Tough jobGSD 2012-08-31 19:23
- C/D for EMA? Good luck! Helmut 2012-09-01 15:09
- Surprise? d_labes 2012-09-05 12:57
- Got it. Ages for sims to complete Helmut 2012-09-05 13:35
- Tough jobGSD 2012-08-31 19:23
- Tough job Helmut 2012-08-31 18:37
- Power for Two stage Design K2K 2013-10-07 14:43
- Power for Two stage Design Helmut 2013-10-07 14:59
- Power for Two stage Design K2K 2013-10-08 14:35
- “Interim power” Helmut 2013-10-08 14:58
- “Interim power” K2K 2013-10-09 12:39
- Validation of PowerTOST Helmut 2013-10-09 14:10
- Phoenix/WinNonlin - power d_labes 2013-10-09 16:11
- Phoenix/WinNonlin - power Helmut 2013-10-09 18:19
- power K2K 2013-10-10 08:36
- Phoenix/WinNonlin - power Helmut 2013-10-09 18:19
- “Interim power” K2K 2013-10-09 12:39
- “Interim power” Helmut 2013-10-08 14:58
- Power for Two stage Design K2K 2013-10-08 14:35
- Power for Two stage Design Helmut 2013-10-07 14:59
- Potvin’s 2-stage adaptive design + RSABE/ABEL GSD 2012-08-31 16:30
- Potvin’s 2-stage adaptive design + RSABE/ABEL Helmut 2012-08-18 00:39
Ing. Helmut Schütz