Reference-scaling: Don’t use FARTSSIE! [Power / Sample Size]
❝ Just few words in defence of FARTSSIE. May be the approximations are rude, far from exact PowerTOST (see #), but the results overally seems to be correlated for CV>30%:
Nope. The EMA’s ABEL not only means extending the limits (based on the observed – not the assumed CVwR) but also assessing the GMR-restriction. It’s a complex framework and therefore, no simple formula exists to calculate power. Try this one:
library(PowerTOST)
CV <- c(30, 40, 50)
n <- c(40, 27, 23)
n.FARTSSIE <- n + n %% 2 # round to next even
res <- data.frame(CV=CV, n.FARTSSIE=n.FARTSSIE, pwr.FARTSSIE=NA,
n.ABE=NA, pwr.ABE=NA, n.ABEL=NA, pwr.ABEL=NA)
names(res)[1] <- "CV%"
EL <- scABEL(CV=CV/100)
for (j in seq_along(CV)) {
# power for ABEL with n of FARTSSIE
res[j, "pwr.FARTSSIE"] <- power.scABEL(CV=CV[j]/100, design="2x2x4",
n=n.FARTSSIE[j])
# PowerTOST's function for ABE mimicking FARTSSIE
tmp <- sampleN.TOST(CV=CV[j]/100, theta0=0.9, theta1=EL[[j, "lower"]],
design="2x2x4", print=FALSE, details=FALSE)
res[j, "n.ABE"] <- tmp[["Sample size"]]
res[j, "pwr.ABE"] <- tmp[["Achieved power"]]
# PowerTOST's function for ABEL (1e5 simulations)
tmp <- sampleN.scABEL(CV=CV[j]/100, theta0=0.9, design="2x2x4",
print=FALSE, details=FALSE)
res[j, "n.ABEL"] <- tmp[["Sample size"]]
res[j, "pwr.ABEL"] <- tmp[["Achieved power"]]
}
print(signif(res, 5), row.names=FALSE)
CV% n.FARTSSIE pwr.FARTSSIE n.ABE pwr.ABE n.ABEL pwr.ABEL
30 40 0.85247 40 0.80999 34 0.80281
40 28 0.78286 28 0.81790 30 0.80656
50 24 0.75363 24 0.83042 28 0.81428
For all CVs FARTSSIE’s sample sizes will give the desired power for ABE (column
pwr.ABE
) but not for ABEL (column pwr.FARTSSIE
). For CV 30% it will be too high (since only 34 subjects are required) but for CV >30% too low (more subjects are required). Only sampleN.scABEL()
will give sample sizes (n.ABEL
) with at least the desired power (pwr.ABEL
).As expected, FARTSSIE screws completely up if one wants to assess the Type I Error. Set “Method C1” and the 4-period replicate. Try with CV 30%, T/R 125%, sample size 34. I got
version power
2.2 5%
1.8 4.99%
1.7 4.99%
library(PowerTOST)
cat(paste0(100*power.scABEL(CV=0.3, design="2x2x4", theta0=1.25,
n=34, nsims=1e6), "%\n"))
8.1626%
Dif-tor heh smusma 🖖🏼 Довге життя Україна!
![[image]](https://static.bebac.at/pics/Blue_and_yellow_ribbon_UA.png)
Helmut Schütz
![[image]](https://static.bebac.at/img/CC by.png)
The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Complete thread:
- Sample Size Estimation -Replicate design- BE limits cakhatri 2017-11-30 09:44 [Power / Sample Size]
- Reference-scaling: Don’t use FARTSSIE! Helmut 2017-11-30 10:58
- Reference-scaling: Don’t use FARTSSIE? Astea 2017-11-30 22:50
- Reference-scaling: Don’t use FARTSSIE!Helmut 2017-12-01 11:42
- Reference-scaling: USE PowerTOST Astea 2017-12-01 14:16
- Reference-scaling: USE PowerTOST cakhatri 2017-12-04 06:00
- Reference-scaling: USE PowerTOST Helmut 2017-12-04 15:07
- Reference-scaling: USE PowerTOST cakhatri 2017-12-05 05:33
- Reference-scaling: USE PowerTOST Helmut 2017-12-04 15:07
- Use PowerTOST d_labes 2017-12-06 09:52
- Use PowerTOST, not Endrényi L, Tóthfalusi L tables mittyri 2017-12-07 16:03
- Precision in Endrényi L, Tóthfalusi L tables d_labes 2017-12-07 18:21
- Precision of PowerTOST mittyri 2017-12-08 22:56
- Precision of PowerTOST Helmut 2017-12-09 17:00
- Precision of PowerTOST mittyri 2017-12-09 21:05
- Precision of PowerTOST Astea 2017-12-10 00:10
- Precision of PowerTOST Helmut 2017-12-10 20:27
- Precision of PowerTOST Astea 2017-12-10 21:13
- Precision of PowerTOST Helmut 2017-12-10 20:27
- Precision of PowerTOST Astea 2017-12-10 00:10
- Precision of PowerTOST mittyri 2017-12-09 21:05
- Precision of PowerTOST Helmut 2017-12-09 17:00
- Precision of PowerTOST mittyri 2017-12-08 22:56
- Precision in Endrényi L, Tóthfalusi L tables d_labes 2017-12-07 18:21
- Use PowerTOST, not Endrényi L, Tóthfalusi L tables mittyri 2017-12-07 16:03
- Reference-scaling: USE PowerTOST cakhatri 2017-12-04 06:00
- Reference-scaling: USE PowerTOST Astea 2017-12-01 14:16
- Reference-scaling: Don’t use FARTSSIE!Helmut 2017-12-01 11:42
- Reference-scaling: Don’t use FARTSSIE! pjs 2018-02-09 13:08
- Reference-scaling: Don’t use FARTSSIE! Helmut 2018-02-09 20:15
- Reference-scaling: Don’t use FARTSSIE? Astea 2017-11-30 22:50
- Reference-scaling: Don’t use FARTSSIE! Helmut 2017-11-30 10:58