Visualization [GxP / QC / QA]

posted by Helmut Homepage – Vienna, Austria, 2021-09-18 15:26 (80 d 05:32 ago) – Posting: # 22588
Views: 1,216

Hi ElMaestro,

» […] it makes very good sense to plot for example the RMSE, CV, SE of diff., or even the width of the CI as function of (cumulated) number of subjects.

If you have all data, of course. A simple visualization using the res data.frame of my previous post:

[image]




windows(width = 5.5, height = 5.5)
op <- par(no.readonly = TRUE)
par(mar = c(3, 4, 2, 0), cex.axis = 0.9, cex.main = 1, font.main = 1)
split.screen(c(length(CRO), length(metric)))
scrn <- 0
for (j in seq_along(CRO)) {
  for (k in seq_along(metric)) {
    scrn <- scrn + 1
    screen(scrn)
    plot(c(0.5, length(study)+0.5), rep(100, 2), type = "n",
         ylim = range(res$lower[res$CRO == CRO[j] & res$metric == metric[k]],
                      res$upper[res$CRO == CRO[j] & res$metric == metric[k]]),
         log = "y", xlab = "", ylab = "PE, 90% CI", axes = FALSE,
         main = paste0(CRO[j], ": ", metric[k]))
    axis(2, las = 1)
    axis(1, at = seq_along(study), tick = FALSE,
         labels = paste("n =", res$n[res$CRO == CRO[j] &
                               res$metric == metric[k]]))
    abline(h = c(80, 100, 125), col = c("red", "black", "red"))
    box()
    for (l in seq_along(study)) {
      arrows(x0 = l,
             y0 = res$lower[res$CRO == CRO[j] & res$metric == metric[k] &
                            res$study == study[l]],
             y1 = res$upper[res$CRO == CRO[j] & res$metric == metric[k] &
                            res$study == study[l]], length = 0.08,
             angle = 90, lwd = 2, code = 3)
      points(l, res$PE[res$CRO == CRO[j] & res$metric == metric[k] &
                       res$study == study[l]], pch = 19, cex = 1.25)
    }
  }
}
close.screen(all = TRUE)
par(op)


Dif-tor heh smusma 🖖
Helmut Schütz
[image]

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

Complete thread:

Activity
 Admin contact
21,788 posts in 4,557 threads, 1,548 registered users;
online 8 (0 registered, 8 guests [including 6 identified bots]).
Forum time: Tuesday 19:59 CET (Europe/Vienna)

A big computer, a complex algorithm and a long time
does not equal science.    Robert Gentleman

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