bear v2.0.1 (upwards) cont'd [🇷 for BE/BA]

posted by ElMaestro  – Denmark, 2008-10-27 21:36 (6021 d 02:05 ago) – Posting: # 2585
Views: 31,394

❝ In this case, can bear still be used to analyze the imbalanced data of a BE study only with lm?


Dear Dr Lee,

yes, you can easily do it with lm or glm as far as a 2-sequence, 2-period, 2-treatment study goes.
Do it this way:

MyFunkyFit=lm(LnParam~Subj+Seq+Pe+Treatm)
(You can use glm is stead of lm here, no problem)
The for the anova...
Anova with type I SS goes something like this:
A_typeI=anova(MyFunkyFit)
Anova with type III goes SS something like this:
A_typeIII=drop1(MyFunkyFit, test="F")

It is correct that I earlier suggested the use of lme in stead. The result wil be exactly the same, it needs to be said. I proposed that because I saw a thread in another forum which indicated that lm might be unstable or incorrect for imbalanced data. This seems not to be the case in practice; I have really tried hard to find a dataset that shows this phenomenon butI can't. Thus lm or lme or glm, they will all work, the choice is yours.

Good luck.
EM.

Complete thread:

UA Flag
Activity
 Admin contact
23,424 posts in 4,927 threads, 1,670 registered users;
20 visitors (0 registered, 20 guests [including 4 identified bots]).
Forum time: 00:41 CEST (Europe/Vienna)

The true Enlightenment thinker, the true rationalist,
never wants to talk anyone into anything.
No, he does not even want to convince;
all the time he is aware that he may be wrong.    Karl R. Popper

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