Bioequivalence and Bioavailability Forum • Why simulate a simple AB|BA at all?

Why simulate a simple AB|BA at all? [RSABE / ABEL]

posted by Helmut – Vienna, Austria, 2014-07-21 18:14 (4359 d 13:47 ago) – Posting: # 13284
Views: 15,598

Hi ElMaestro,

❝ d_labes should publish a commentary in the journal. I think his figures were sort of more telling weren't they?

Yes. Given the unpleasant experience we had last year submitting a letter to the namely journal I’m not sure whether he will risk the efforts…

BTW, I have some mixed feelings about the paper. I don’t have the slightest idea why the authors simulated the rejection rate for a conventional 2×2 cross-over. Power can be directly calculated for any given combination of α, CV, GMR, and N. One should never ever get anything >0.05! So where does this hump at N>30 in Fig. 1 come from?
Try:

library(PowerTOST) n <- seq(8, 100, 2) CV <- c(10, 20, seq(30, 55, 5)) pBE <- vector("numeric", length=length(n)) clr <- colorRampPalette(c("blue", "red"))(length(CV)) for(j in seq_along(CV)) { for(k in seq_along(n)) { pBE[k] <- power.TOST(CV=CV[j]/100, theta0=1.25, n=n[k]) if(j == 1 & k == length(n)) { plot(n, pBE, type="l", ylim=c(0, 0.05), las=1, lwd=2, col=clr[j]) abline(h=0.05, lty=3) } } lines(n, pBE, type="l", lwd=2, col=clr[j]) text(n[j], pBE[j], labels=paste0(CV[j],"%")) }

Another point are the number of simulations. We know the slow convergence in these kind of sim’s. 5,000 for power and 10,000 for empiric α are by a factor of 100 too low.

❝ […] one of the authors used to be a member of the PK subgroup back in the day.

Interesting.

—
Dif-tor heh smusma 🖖🏼 Довге життя Україна!
Helmut Schütz

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes

Complete thread:

EMA: α-inflation – the suspicion begins to mount Helmut 2014-07-21 02:04
- EMA: α-inflation – the suspicion begins to mount ElMaestro 2014-07-21 09:24
  - Why simulate a simple AB|BA at all?Helmut 2014-07-21 16:14
    - Why simulate a simple AB|BA at all? ElMaestro 2014-07-21 20:50
      - Fancy smoothing? Helmut 2014-07-21 23:13
        
        Arbitrary smoothing? d_labes 2014-07-22 08:43
        
        Noise… Helmut 2014-07-22 13:31
        
        TSD Japonica… d_labes 2014-07-22 16:06
        
        TSD Japonica… Helmut 2014-07-22 17:50
        
        Noise debugged d_labes 2014-07-24 13:47
        
        Noise debugged Helmut 2014-07-24 15:07
        
        Shit happens d_labes 2014-07-24 16:09
      - Commentary d_labes 2014-07-22 08:18
        
        Commentary nobody 2014-09-15 08:24
        
        Commentary Helmut 2014-09-15 10:12
      - IBE/PBE = Two-Stage Helmut 2014-09-29 03:33
        
        IBE/PBE = Two-Stage ElMaestro 2014-09-29 15:16
        
        Sequential Design = Inflation likely… Helmut 2014-09-30 15:03