lme() in bear [🇷 for BE/BA]

posted by ElMaestro  – Denmark, 2015-04-18 13:28 (4089 d 23:44 ago) – Posting: # 14698
Views: 33,176

Hi yung-jin,

❝ ❝ 1. Could you try and fit fixed effects as log(Cmax) ~ 0+ drug + seq + prd, and then extract your drug effects directly from that.


❝ OK. add an intercept?


No, take away an intercept.

❝ Fixed effects: log(Cmax) ~ 0 + seq + prd + drug


In a sense this isn't what I suggested. Please try and fit it with drug specified as the first effect. In stead of
log(Cmax) ~ 0 + seq + prd + drug
see if you can make sure it somehow fits
log(Cmax) ~ 0 + drug + prd + seq
or equally good
log(Cmax) ~ 0 + drug + seq + prd

order of effects has lexical importance and determines how many effect estimates you get per term. Accordingly, when you fit sequence as the first term you will not see one effect estimate for each drug.

Good luck and sorry if my initial suggestion was not too well described.

Pass or fail!
ElMaestro
Thread locked

Complete thread:

UA Flag
Activity
 Admin contact
23,655 posts in 4,993 threads, 1,570 registered users;
260 visitors (0 registered, 260 guests [including 14 identified bots]).
Forum time: 13:12 CEST (Europe/Vienna)

Most scientists today are devoid of ideas, full of fear, intent on
producing some paltry result so that they can add to the flood
of inane papers that now constitutes “scientific progress”
in many areas.    Paul Feyerabend

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