Groups: Overlapping CIs [Design Issues]

posted by BEQool  – 2024-11-06 08:44 (238 d 07:27 ago) – Posting: # 24262
Views: 6,340

Hello Helmut

❝ Let’s try a less extreme case with \(\small{\mu_1=0.825,\,\mu_2=1/\mu_1}\):

❝ Simulated data

❝   n = 32

❝   group 1: n = 16, mue = 0.825

❝   group 2: n = 16, mue = 1.2121

❝ Model I  (pooled data)

❝   p(G×T) = 0.040949

❝ Model II (pooled data)

❝   PE     = 103.96%

❝   90% CI =  92.58 – 116.73%

❝   CVw    =  27.80%

❝ Model III (group 1)

❝   PE     =  90.57%

❝   90% CI =  75.27 – 108.96%

❝   CVw    =  30.37%

❝ Model III (group 2)

❝   PE     = 119.33%

❝   90% CI = 104.67 – 136.03%

❝   CVw    =  21.28%

❝ \(\small{p(\text{G}\times\text{T})}\) is significant and CIs of groups overlap. :-D


Yes true. The variability of group 1 is quite high - if we had similar variability than in group 2, then the 90% CIs wouldnt overlap :-D But then again, it makes sense and we all know that with larger sample size and lower variability we get narrower CIs and lesser chance of them overlapping so yes as can be seen it depends on case-by-case basis. :-)

Complete thread:

UA Flag
Activity
 Admin contact
23,425 posts in 4,928 threads, 1,681 registered users;
61 visitors (0 registered, 61 guests [including 7 identified bots]).
Forum time: 17:12 CEST (Europe/Vienna)

No problem can stand the assault of sustained thinking.    Voltaire

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