PowerTOST: CVfromCI [Study As­sess­ment]

posted by Helmut Homepage – Vienna, Austria, 2019-02-20 13:00 (1225 d 22:44 ago) – Posting: # 19937
Views: 9,152

¡Hola Rosy!

» Dear Helmut,

             Not interested in other members’ opinions?

» If i found an article of a BABE study in which 3 formulation where evaluated against to reference (A) in a 4 way crossover study, …

So far, so good.

» … but in a bioequivalence table appears for example A vs B treatment and its respective Geometric Mean Ratio (IC 90%).

Being A the reference, it should be B vs A, right?

» If i wanna calculate CV% intrasubject ussing POWER.TOST which desing i have to pick up (4x4 or parallel)? Of course 4x4 is the real design but the comparative A vs B is technically a parallel study.

Parallel‽
You have to find out whether the study was evaluated with a “pooled ANOVA” or according to the “Two‐at‐a‐Time Principle” (see this post).
Example: 4×4 crossover, n 24, 90% CI 85.00–106.18%.

#############################################
n    <- 24        # total sample size
l    <- 0.8500    # lower 90% CL
u    <- 1.0618    # upper 90% CL
#############################################
library(PowerTOST)
des  <- "4x4"     # design and 1st evaluation
eval <- "2x2"     # 2nd evaluation
pe   <- sqrt(l*u) # calculate the PE
CV.1 <- CVfromCI(lower=l, upper=u, design=des, n=n)  # 1
CV.2 <- CVfromCI(lower=l, upper=u, design=eval, n=n) # 2
cat(paste0("\n", des, " design, n = ", n,
           sprintf("%s %.2f%%%s", "\n90% CI =", 100*l, "\u2013"),
           sprintf("%.2f%%", 100*u),
           sprintf(" %s %.2f%%)", "(PE =", 100*pe),
           sprintf("\n  Pooled ANOVA           : CVintra = %.2f%%",
                   100*CV.1),
           sprintf("\n  Two-at-a-Time Principle: CVintra = %.2f%%",
                   100*CV.2)), "\n")

You will get:

4x4 design, n = 24
90% CI = 85.00%–106.18% (PE = 95.00%)
  Pooled ANOVA           : CVintra = 23.41%
  Two-at-a-Time Principle: CVintra = 22.73%


How to discover which method was used?
Work backwards, i.e., see with which CV you can reproduce the reported results for each comparison. (Nonsense: See Detlews post below)

res.1 <- CI.BE(pe=pe, CV=CV.1, n=n, design=des)
res.2 <- CI.BE(pe=pe, CV=CV.2, n=n, design=eval)
cat(paste0("\nBack-calculated 90% CI by",
    "\n  Pooled ANOVA           : ",
    sprintf("%.2f%%%s", 100*res.1[["lower"]], "\u2013"),
    sprintf("%.2f%%", 100*res.1[["upper"]]),
    "\n  Two-at-a-Time Principle: ",
    sprintf("%.2f%%%s", 100*res.2[["lower"]], "\u2013"),
    sprintf("%.2f%%", 100*res.2[["upper"]]), "\n"))

Back-calculated 90% CI by
  Pooled ANOVA           : 85.00%–106.18%
  Two-at-a-Time Principle: 85.00%–106.18%


Dif-tor heh smusma 🖖 [image]
Helmut Schütz
[image]

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

Complete thread:

UA Flag
Activity
 Admin contact
22,181 posts in 4,647 threads, 1,572 registered users;
online 9 (0 registered, 9 guests [including 6 identified bots]).
Forum time: Thursday 12:44 CEST (Europe/Vienna)

The only way to comprehend what mathematicians mean by Infinity
is to contemplate the extent of human stupidity.    Voltaire

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5