Bioequivalence and Bioavailability Forum • Geometric mean in plots

Geometric mean in plots [🇷 for BE/BA]

posted by Helmut – Vienna, Austria, 2013-03-27 15:18 (4466 d 11:09 ago) – Posting: # 10295
Views: 12,188

Hi Yung-jin,

❝ However, the question is all data points cannot be zero (the first data point is the case?) or strictly speaking all data points must greater than 1.0 (otherwise, it will cause negative values, such as log10(0.65)). It may be quite common to have some Cp < 1.0 in BE study. In R, there is some packages that can ignore that, such as the option 'zero.rm(foo)'; however, these packages are still not available for R3.0.0.

Problems arise if at least one concentration is <LLOQ. Some people (like me) don’t report the geometric mean for this time point, others calculate the mean if ⅔ or ½ of concentrations are >LLOQ (excluding the BQLs). For the plots I would suggest to use backtransformed values – either in linear scale or with a log-axis.

—
Dif-tor heh smusma 🖖🏼 Довге життя Україна!
Helmut Schütz

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

Complete thread:

Bear: feature requests Helmut 2010-12-08 15:48
- Bear: feature requests yjlee168 2010-12-08 18:49
  - Bear: feature requests Helmut 2010-12-08 19:48
  - Bear: feature requests d_labes 2010-12-09 08:48
    - Bear: feature requests Helmut 2010-12-09 14:20
      - Bear: feature requests yjlee168 2010-12-09 20:24
    - Bear: feature requests yjlee168 2010-12-09 19:57
      - Bear: feature requests Aceto81 2010-12-13 10:26
        
        Bear: feature requests yjlee168 2010-12-13 13:29
- Geometric mean? re: Bear: feature requests yjlee168 2013-03-27 13:21
  - Geometric mean in plotsHelmut 2013-03-27 14:18
    - Geometric mean in plots yjlee168 2013-03-27 21:16