Bravo? [General Sta­tis­tics]

posted by ElMaestro  – Denmark, 2011-09-02 20:48 (5399 d 21:27 ago) – Posting: # 7329
Views: 8,528

Dear d_labes,

❝ The statistics you do here is at least very approximative.


yes, just like mandatory parametric evaluation of CI's even when residuals are non-normal. But we never do a parametric test when we don't know the distribution of residuals do we? :-D

To be honest, I had no thought of your point at all when I wrote the post above. I guess one can argue that, there's probably both intra-row and intra-column correlation (same subject experiencing AEs in two or more categories for the same treatment, as well as same subject experiencing AE with test and ref respectively. There's always a whining subject with a ton of AEs, especially if the trial is in a Western country).

To HS: I had no idea Fisher's exact test could be done on tables larger than 2x2... This great forum is an eternal source of knowledge. Thank you for improving the statistic for Dr_Dan as well as extending my horizon.

Pass or fail!
ElMaestro

Complete thread:

UA Flag
Activity
 Admin contact
23,654 posts in 4,992 threads, 1,570 registered users;
121 visitors (0 registered, 121 guests [including 29 identified bots]).
Forum time: 18:15 CEST (Europe/Vienna)

The idea is to try and give all the information to help others
to judge the value of your contribution;
not just the information that leads to judgment
in one particular direction or another.    Richard Feynman

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