Site and Treatment as fixed. [General Sta­tis­tics]

posted by ElMaestro  – Denmark, 2016-06-09 21:39 (3315 d 21:12 ago) – Posting: # 16421
Views: 7,010

Hi Dr Ripal,

❝ We have been asked by USFDA to include site/centre effect in one of our multicenteric oncology bioequivalence study. Kindly suggest which statistical tests should be used for the same.


BE in oncology often means a parallel design, so I think you will need a simple two-factor model with treatment and site as fixed effects in a PROC GLM or equivalent.

Pass or fail!
ElMaestro

Complete thread:

UA Flag
Activity
 Admin contact
23,428 posts in 4,929 threads, 1,697 registered users;
55 visitors (0 registered, 55 guests [including 22 identified bots]).
Forum time: 18:52 CEST (Europe/Vienna)

Anyone who conducts an argument by appealing to authority
is not using his intelligence;
he is just using his memory.    Leonardo da Vinci

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