the model matrix and the contrasts [🇷 for BE/BA]

posted by mittyri – Russia, 2024-02-22 21:21 (87 d 12:45 ago) – Posting: # 23873
Views: 865

Dear ElMaestro!

I (and many others) understand your degree of discontent.
Yes, this is something unexpected.
I suppose you already read this answer

I have nothing to add to this: that's a price for identifiability. The only solution I see besides you already gave is to turn off the contrasts as shown there:
f <- sample(gl(3, 4, labels = letters[1:3]))
# [1] c a a b b a c b c b a c
#Levels: a b c

g <- sample(gl(3, 4, labels = LETTERS[1:3]))
# [1] A B A B C B C A C C A B
#Levels: A B C
X0 <- model.matrix(~ f + g, contrasts.arg = list(
                   f = contr.treatment(n = 3, contrasts = FALSE),
                   g = contr.treatment(n = 3, contrasts = FALSE)))

#   (Intercept) f1 f2 f3 g1 g2 g3
#1            1  0  0  1  1  0  0
#2            1  1  0  0  0  1  0
#3            1  1  0  0  1  0  0
#4            1  0  1  0  0  1  0
#5            1  0  1  0  0  0  1
#6            1  1  0  0  0  1  0
#7            1  0  0  1  0  0  1
#8            1  0  1  0  1  0  0
#9            1  0  0  1  0  0  1
#10           1  0  1  0  0  0  1
#11           1  1  0  0  1  0  0
#12           1  0  0  1  0  1  0

Kind regards,
Mittyri

Complete thread:

UA Flag
Activity
 Admin contact
23,033 posts in 4,835 threads, 1,643 registered users;
45 visitors (0 registered, 45 guests [including 14 identified bots]).
Forum time: 11:07 CEST (Europe/Vienna)

Competence, like truth, beauty and contact lenses,
is in the eye of the beholder.    Laurence J. Peter

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