Bioequivalence and Bioavailability Forum

Hi to the North!

❝ […] Maybe it's tooooo new after all.

Maybe. Sample sizes are not that bad. The FDA requires tighter release spec’s. Hence, we implemented 0.975 as the default in PowerTOST.

library(PowerTOST)
CVwR <- 0.1 # e.g., Cmax of valproic acid (AUC has ~0.05).
s.r  <- 1   # ratio of swT/swR
CVwT <- mse2CV(CV2mse(CVwR)*s.r)
sampleN.NTIDFDA(CV=c(CVwT, CVwR), details=FALSE)

+++++++++++ FDA method for NTID's +++++++++++
           Sample size estimation
---------------------------------------------
Study design:  2x2x4
log-transformed data (multiplicative model)
1e+05 studies for each step simulated.

alpha  = 0.05, target power = 0.8
CVw(T) = 0.1, CVw(R) = 0.1
True ratio     = 0.975
ABE limits     = 0.8 ... 1.25
Regulatory settings: FDA

Sample size
 n     power
18   0.841790

No problem.

Now s_wT∕s_wR 2.

s.r  <- 2
CVwT <- mse2CV(CV2mse(CVwR)*s.r)
sampleN.NTIDFDA(CV=c(CVwT, CVwR), details=FALSE)

+++++++++++ FDA method for NTID's +++++++++++
           Sample size estimation
---------------------------------------------
Study design:  2x2x4
log-transformed data (multiplicative model)
1e+05 studies for each step simulated.

alpha  = 0.05, target power = 0.8
CVw(T) = 0.1417745, CVw(R) = 0.1
True ratio     = 0.975
ABE limits     = 0.8 ... 1.25
Regulatory settings: FDA

Sample size
 n     power
28   0.817760

Still easy.

Boehringer’s formulation change. The family’s slaves planned for T/R 0.85 (tried at lot, couldn’t do better), a CV_wR of 80%, and RSABE (old guidance). That’s the infamous 4-period full replicate study in 180 subjects on ClinicalTrials.gov.
Nowadays:

sampleN.NTIDFDA(CV=0.8, theta0=0.85, details=FALSE)

+++++++++++ FDA method for NTID's +++++++++++
           Sample size estimation
---------------------------------------------
Study design:  2x2x4
log-transformed data (multiplicative model)
1e+05 studies for each step simulated.

alpha  = 0.05, target power = 0.8
CVw(T) = 0.8, CVw(R) = 0.8
True ratio     = 0.85
ABE limits     = 0.8 ... 1.25
Regulatory settings: FDA

Sample size
  n    power
836  0.800870

Oops.