Sex-by-treatment interaction [Design Issues]

posted by Helmut Homepage – Vienna, Austria, 2023-05-05 14:44 (142 d 11:59 ago) – Posting: # 23544
Views: 709

Hi BEQool,

❝ […] is Gender*Treatment also a between-subject factor (like Sequence and Gender here)?

If you replace gender by sex, yes. Muse about it. ;-) BTW, you could even drop sequence from the model

❝ In the article Evaluation of sex-by-formulation interaction in bioequivalence studies of efavirenz tablets by González-Rojano et al. it doesnt say anything about which factor they used (within- or between-subject) to test Gender*Treatment interaction.

See p. 1731, right column, top. That’s the model proposed by the FDA earlier:*$$\eqalign{Y&|\;\text{sequence},\,\text{sex},\,\text{sequence}\,\times\,\text{sex},\\
&\phantom{|}\;\text{treatment},\,\text{sex}\,\times\,\text{treatment}}$$ I employed it also in my meta-analysis. The ‘purpose’ of this model is only to assess the interaction. Since treatment appears twice in the model, it is not possible to get an unbiased estimate of it (for a similar story see this article).

❝ Additionally, how do you know which factor is a within-subject and which is a between-subject? If anyone has an explanation in simple words :-)

In simple words? I’ll try. For a given subject anything which remains constant throughout a study leads to a between-subject factor (e.g., sex, sequence, stage, group, site). Everything else leads to a within-subject factor (e.g., treatment, period).

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz

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

Complete thread:

UA Flag
 Admin contact
22,759 posts in 4,775 threads, 1,627 registered users;
18 visitors (0 registered, 18 guests [including 3 identified bots]).
Forum time: 02:44 CEST (Europe/Vienna)

In God we trust;
all others must bring data.    W. Edwards Deming

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