Loky do
★    

Egypt,
2020-10-12 23:38
(410 d 02:07 ago)

Posting: # 21994
Views: 785
 

 statistical calculation procedures for 4 arm studies [General Sta­tis­tics]

Dears

In case of four way, two sequences, four periods BE study, the 1st two periods done under fasting conditions and the 2nd two periods under fed conditions on the same volunteers, Are the statistical calculations (CI, ANOVA) for each study (fast and fed) calculated separately or not If i need to demonstrate bioequivalence between test & reference products under fast & fed conditions?
Thanks all in advance
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2020-10-12 23:58
(410 d 01:47 ago)

@ Loky do
Posting: # 21995
Views: 659
 

 4 periods (BE fed & fasting)

Hi Loky do,

do you mean sumfink like this?
If yes, perform two separate ANOVAs on part 1 (T vs R in fed state: periods 1 & 2) and part 2 (T vs R in fasting state: periods 3 & 4).
To assess the food effects (fed vs fasting) of T and R employ two separate paired comparisons. Here you have to assume no period effects – state that in the protocol. However, you will not loose the war on this if you succeeded in showing BE in fed and fasting state. There are no commonly accepted rules to decide whether food effects are different. In my studies I assess whether the CIs overlap.

Homework: Find out why I recommend fed state first. ;-)

Dif-tor heh smusma 🖖
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Activity
 Admin contact
21,778 posts in 4,555 threads, 1,547 registered users;
online 8 (0 registered, 8 guests [including 7 identified bots]).
Forum time: Saturday 00:45 CET (Europe/Vienna)

Every new technology to me is like a newborn baby –
and you think that it’s become president
or it’s cure cancer or win a nobel prize.
But in the end, you’re perfectly happy
when it just stays out of jail […].    Eric Betzig

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