Bioequivalence and Bioavailability Forum • Two groups (e.g. logistics)

Two groups (e.g. logistics) [Design Issues]

posted by Helmut – Vienna, Austria, 2007-11-16 16:07 (6428 d 17:53 ago) – Posting: # 1303
Views: 13,200

Dear Sangeea,

since I recently had to deal with deficiency letters from the Gulf States (Saudia Arabia, Emirates), I would suggest the following procedure:

Fixed: Sequence + Treatment + Period + Group + Treatment × Group Random: Subject(Sequence)

Tests for Group and Treatment × Group.

If the ‘Treatment × Group Interaction’ term is statistically not significant (p>0.05), the simple model (i.e., naïve pooling of data without both Group-terms) can be applied.*

S Bolton S, Bon C. Pharmaceutical Statistics. New York: Marcel Dekker; 4^th ed. 2004. p. 344–5.

—
Dif-tor heh smusma 🖖🏼 Довге життя Україна!
Helmut Schütz

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

Complete thread:

Statistical Analysis Plan sangeeta 2007-06-25 16:04 [Design Issues]
- Statistical Analysis Plan M.Vasu 2007-07-02 08:29
  - Two groups (e.g. logistics) Helmut 2007-07-03 19:18
    - Two groups (e.g. logistics) M.Vasu 2007-07-05 08:40
    - Two groups (e.g. logistics) sangeeta 2007-07-21 12:05
      - Two groups (e.g. logistics)Helmut 2007-11-16 15:07
        
        Two groups (e.g. logistics) MGR 2007-11-26 06:55
        
        Two groups (e.g. logistics) Helmut 2007-11-26 11:49
        
        Two groups (e.g. logistics) arl_stat 2013-03-26 09:42
- Statistical Analysis Plan MGR 2007-07-02 13:27