intra-subject correlation [Regulatives / Guidelines]

posted by Helmut Homepage – Vienna, Austria, 2011-11-25 18:16 (5326 d 23:28 ago) – Posting: # 7725
Views: 10,739

Dear Martin!

❝ This is extremely interesting. I would by happy if you can you provide some summary regarding the correlation between time points. (e.g. was the correlation constant over time, …).


As I told you last Wednesday at the ‘debriefing’ I would need a month of spare time to retrieve them (~100,000 data pairs in various formats). I can only serve with an overview. 133 cross-over studies, 2843 subjects, AUCt or AUCτ:

[image]

[image]              min      2.5%     med      97.5%    max
R²            0.0480   0.1905   0.6517   0.9111   0.9639
R²adj         0.0047   0.1606   0.6329   0.9022   0.9623
sample size   6       12       20       48       52


R² of my sample has an interesting distribution…

Of course, correlation depends on the sample size* – but you get an impression.
Studies with low correlations contained one ‘outlier’ each but were still large enough to show BE (well, that was my selection bias).

[image]


Sponsors :love: n=24.



Dif-tor heh smusma 🖖🏼 Довге життя Україна! [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
23,655 posts in 4,993 threads, 1,570 registered users;
377 visitors (0 registered, 377 guests [including 25 identified bots]).
Forum time: 18:44 CEST (Europe/Vienna)

Ignorance more frequently begets confidence
than does knowledge.    Charles Darwin

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