Log in
RegisterWell roared, lion [Two-Stage / GS Designs]
Dear Helmut!
Full ACK!
From some sparse own simulations I did (Potvin B, Nmax=120) in the past I can add:
Patient's risk found below 5%, power fairly above 80% if first stage N is not too small and CV<30%. For CV>30% (30, 35 and 40% simulated) a remarkable decrease in power was seen.
But these simulations didn't cover the full range of CV and n(stage1) to assure that patient's risk is bound to ≤0.05 under all circumstances.
❝ If you are including a fixed sample size in your method you are leaving the validated range covered by the papers. Intuitively I would say you are only jeopardizing power (higher producer’s risk) – but actually I don’t know whether the patient’s risk is unaffected.
Full ACK!
From some sparse own simulations I did (Potvin B, Nmax=120) in the past I can add:
Patient's risk found below 5%, power fairly above 80% if first stage N is not too small and CV<30%. For CV>30% (30, 35 and 40% simulated) a remarkable decrease in power was seen.
But these simulations didn't cover the full range of CV and n(stage1) to assure that patient's risk is bound to ≤0.05 under all circumstances.
—
Regards,
Detlew
Regards,
Detlew
Complete thread:
- 2-Stage design balakotu 2012-06-21 08:28
![[Mix]](https://static.bebac.at/img/mix.png "open in Mix view")
- Sequential design, maximum sample size in stage 2 Helmut 2012-06-21 16:05
- Sequential design, maximum sample size in stage 2 ElMaestro 2012-06-22 01:43
- Well roared, liond_labes 2012-06-22 08:45
- Sequential design, maximum sample size in stage 2 Helmut 2012-06-21 16:05
Ing. Helmut Schütz