Nitpicker! [Two-Stage / GS Designs]

posted by ElMaestro  – Denmark, 2017-08-22 15:27 (1355 d 16:17 ago) – Posting: # 17733
Views: 25,006

Hi Hötzi,

» You have a point. IMHO, this question should be answered: yes!


And on basis of this story we will define Hötzi's universal law of BE:
ElMaestro is always right1.


By the way, since you are a speed devotee:
FindCritCV.Sec=function(Pwr.T, GMR, Nps, Is.St2=1, d=.00001, iniCV)
##the secant method has really nasty properties if the ini value is a little off.
{
  CV1=iniCV
  CV2=CV1*1.05
  y2=1
  while (abs(y2)>d)
  {
   y1=Power.calc(Nps, GMR, CV1, Is.St2)-Pwr.T
   y2=Power.calc(Nps, GMR, CV2, Is.St2)-Pwr.T
   CV3= CV2-y2*(CV2-CV1)/(y2-y1)
   CV1=CV2
   CV2=CV3
  }
  return(0.5*(CV1+CV2)) ##or play around
}

(...)
 for (Nps in 6:length(vecCritCVs))
  {
   if (Nps==6) iniCV=min(0.709*GMR-0.552, 0.709/GMR -0.552)
               else iniCV=vecCritCVs[Nps-1]
    vecCritCVs[Nps]<<-FindCritCV.Sec(0.8, GMR, Nps, 1, 1e-10, iniCV)
  }

(...)















Footnote 1:
Except when he isn't. Which also happens. With regrettable frequency...:-D

Pass or fail!
ElMaestro

Complete thread:

Activity
 Admin contact
21,445 posts in 4,482 threads, 1,510 registered users;
online 11 (0 registered, 11 guests [including 2 identified bots]).
Forum time: Sunday 07:45 UTC (Europe/Vienna)

It is better to know some of the questions
than all of the answers.    James Thurber

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5