Bioequivalence and Bioavailability Forum

R code for Average BE or parallel design N computations [🇷 for BE/BA]

posted by Achievwin – US, 2022-09-16 06:31 (807 d 13:56 ago) – Posting: # 23300
Views: 4,243

Dear All:

R PowerTOST has a neat code that gives tabular listing of N and power attained for Scaled ABE using the macro below.

Is there a similar code for ABE for 2x2 or parallel design studies. Any help is much appreciated.
(may be a simple thing but I don't know)

Thanks and regards,

Achievwin

sampleN.RSABE(alpha = 0.05, targetpower = 0.80, theta0 = 0.9, theta1 = 0.8, theta2 = 1.25, CV = c(0.46, 0.46),

design = c("2x2x4"), regulator = c("FDA"),

nsims = 1e+05, nstart = 24, imax=100,

print = TRUE, details = TRUE, setseed=TRUE).

---------------------------------------------

Study design: 2x2x3 (3 period full replicate)

log-transformed data (multiplicative model)

1e+05 studies for each step simulated.

alpha  = 0.05, target power = 0.9

CVw(T) = 0.46; CVw(R) = 0.46

True ratio = 0.93

ABE limits / PE constraints = 0.8 ... 1.25 

FDA regulatory settings

- CVswitch            = 0.3 

- regulatory constant = 0.8925742 

- pe constraint applied

Sample size search

 n     power

24   0.72529 

26   0.76284 

28   0.79686 

30   0.82498 

32   0.84757 

34   0.86782 

36   0.88550 

38   0.89948 

40   0.91323

Complete thread:

R code for Average BE or parallel design N computationsAchievwin 2022-09-16 04:31 [🇷 for BE/BA]
- Script for ABE and SABE (any applicable design) Helmut 2022-09-16 13:37
- New article / wacky script Helmut 2022-10-24 16:51
  - New article / wacky script Achievwin 2022-11-11 12:51

R code for Average BE or parallel design N com­pu­ta­tions [🇷 for BE/BA]

Complete thread:

R code for Average BE or parallel design N computations [🇷 for BE/BA]