Potvin et al: effects in stage 2 [Two-Stage / GS Designs]

posted by Helmut Homepage – Vienna, Austria, 2009-10-16 13:32 (4360 d 22:22 ago) – Posting: # 4368
Views: 4,648

Dear Earlybird!

» we are planning a two-stage Design according Method B, Diane Potvin.

Method B = “Gürtel mit Hosenträgern”. SCNR; this is a German proverb for overweariness, which roughly translates into “waistbelt plus suspenders”.

» Does somebody know if the ANOVA statement has to be adapted? I.E. to add stage, stage-treatment interaction as fixed effects and subject nested within (stage × sequence) as random effect.

At least if you proceed to the second stage (see the last page of the methods-section of Potvin’s paper). Just checked it in one of my studies (Method C, which was accepted by the BfArM) – difference in the CI was 0.15% (with/without effects)… However, even if you find significant effects, no poolability criteria are to be applied anyhow.

If you have time, go and meet Diane Potvin in Ottawa.

Dif-tor heh smusma 🖖
Helmut Schütz

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

Complete thread:

 Admin contact
21,694 posts in 4,535 threads, 1,541 registered users;
online 16 (1 registered, 15 guests [including 6 identified bots]).
Forum time: Friday 11:55 CEST (Europe/Vienna)

Tortured data will confess to anything.    Fredric Menger

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