-----Original Message-----
From: R-sig-mixed-models [mailto:r-sig-mixed-models-bounces at r-
project.org] On Behalf Of Ben Bolker
Sent: Thursday, March 12, 2015 19:55
To: r-sig-mixed-models at r-project.org
Subject: Re: [R-sig-ME] Contrast in lme4
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
"How do I set up custom contrasts?" is (1) not specific to mixed
models (so not really appropriate for this list -- maybe try r-help or
Stack Overflow); (2) rather tricky in R (it may be difficult in all
statistics packages/languages, I don't know); and (3) sufficiently
detailed that the information you give below isn't really quite
sufficient. A reproducible example will help when you post your
question somewhere else. You can use the "contrast" package, or the
"multicomp" package, to test contrasts. As far as how the contrasts
are set up, there's a reasonable description in Crawley's _Data
Analysis in S-PLUS_ book, or see
http://www.ats.ucla.edu/stat/r/library/contrast_coding.htm
http://ms.mcmaster.ca/~bolker/classes/s4c03/notes/week2B.pdf
On 15-03-12 01:52 PM, Douglas Bates wrote:
It is better to send questions like this to the
R-SIG-Mixed-Models at R-project.org mailing list, which I am cc:ing on
this reply.
On Thu, Mar 12, 2015 at 3:09 AM adeela uaf <adeela.uaf at gmail.com>
wrote:
Dear Douglas Bates, How to perform contrast analysis for fixed
effects in lme4 package. My data is same as sleepstudy data with
an additional cloumn comprising 12 treatments also. The
structure of the treatmnets is such that: 1) 1 treatment is
control 2) 4 treatments are bio-agents. 3) 3 treatments are
botanical. 4) 2 are bi prodcts 5) 2 are fungisides I want to make
comparison among the groups which differ significantly after
Model<-lmer(Disease~Trt+Date+Trt*Date+(1|Subject),data=YR) Best
Regars, Adeela
[[alternative HTML version deleted]]