Bioequivalence and Bioavailability Forum

More confusion [RSABE / ABEL]

posted by ElMaestro  – Denmark, 2013-04-10 01:29 (4472 d 23:49 ago) – Posting: # 10386
Views: 5,967

Gentlemen...

I have the point estimate and s right, this much is certain.
Since something is wrong, I just need to figure out which n-per-sequence that would result in limits such as the lower one of 107.11:

for (n1 in 30:80)
for (n2 in 30:80)
 {
  df=n1+n2-2
  ct = qt(1-0.05, df)
   lnL=lnPE-s*ct*sqrt(0.25*(1/n1+1/n2))
  if (exp(lnL)>1.0710)
  if (exp(lnL)<1.0712) cat("n1=", n1, "n2=",n2, "lower limit=", exp(lnL), "\n")
 }


The output is:
n1= 34 n2= 77 lower limit= 1.071095
n1= 35 n2= 72 lower limit= 1.071009
n1= 35 n2= 73 lower limit= 1.0712
n1= 36 n2= 69 lower limit= 1.071178
n1= 37 n2= 65 lower limit= 1.07102
n1= 39 n2= 60 lower limit= 1.071096
n1= 40 n2= 58 lower limit= 1.071152
n1= 41 n2= 56 lower limit= 1.071138
n1= 42 n2= 54 lower limit= 1.071052
n1= 44 n2= 51 lower limit= 1.071036
n1= 45 n2= 50 lower limit= 1.071145
n1= 50 n2= 45 lower limit= 1.071145
n1= 51 n2= 44 lower limit= 1.071036
n1= 54 n2= 42 lower limit= 1.071052
n1= 56 n2= 41 lower limit= 1.071138
n1= 58 n2= 40 lower limit= 1.071152
n1= 60 n2= 39 lower limit= 1.071096
n1= 65 n2= 37 lower limit= 1.07102
n1= 69 n2= 36 lower limit= 1.071178
n1= 72 n2= 35 lower limit= 1.071009
n1= 73 n2= 35 lower limit= 1.0712
n1= 77 n2= 34 lower limit= 1.071095

So, realistic n1 and n2 add up to irrelevant values, therefore I might be inclined to believe the problem must be one of these lines:
df=n1+n2-2
ct = qt(1-0.05, df)
lnL=lnPE-s*ct*sqrt(0.25*(1/n1+1/n2))

Complete thread:

• EMA dataset 1 trouble ElMaestro 2013-04-08 20:23 
  • complete (RR) only Helmut 2013-04-09 02:37
  • EMA dataset 1 - programmers trouble d_labes 2013-04-09 09:01
    • Still not exactly sure ElMaestro 2013-04-09 10:12
      • Still not exactly sure - why d_labes 2013-04-09 15:57
        • My problem(s) ElMaestro 2013-04-09 16:39
        • More confusionElMaestro 2013-04-09 23:29
          • Confusion help d_labes 2013-04-10 10:51