Dear Jacques
You may be interested in the answer of Doug Bates to another
post. The question is different, but in the answer there is a
part about testing if a variance component may be zero:
http://finzi.psych.upenn.edu/R/Rhelp02a/archive/51080.html
Hope this helps.
Best regards,
Christoph Bu
n please clarify and maybe someone else can help.
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Jacques VESLOT
Sent: Friday, October 28, 2005 7:22 AM
To: R-help@stat.math.ethz.ch
Subject: [R] Random effect models
Dear R-users,
Sorry for reposting. I put it
Dear R-users,
Sorry for reposting. I put it in another way :
I want to test random effects in this random effect model :
Rendement ~ Pollinisateur (random) + Lignee (random) + Pollinisateur:Lignee
(random)
Of course :
summary(aov(Rendement ~ Pollinisateur * Lignee, data = mca2))
gives wrong tes
