In case the suggested model is NOT what you want, the book by
Pinheiro and Bates describes other models that may be closer to what you
want. Also, you might wish to consider lme in both packages nlme and
lme4. They are different, and overall lme4 is better, though it may not
be in any particular case. Bates is the overall architect for both, and
the list of people who know more about this subject than he does is
exceedingly small.
hope this helps. spencer graves
F Z wrote:
Hi
I suspect that what you want to do is to have a randon intercept for
Rails. i.e.:
m<-lme(travel ~ Rail, data = Rail, random = ~ 1 | Rail)
You might want to try the documentation under C:\Program
Files\R\rw1091\library\lme4\doc and also the book "Mixed-effect models
in S and S-Plus" by Pinheiro and Bates.
Francisco
From: "angel hellraiser" <[EMAIL PROTECTED]>
To: [EMAIL PROTECTED]
Subject: [R] about lme
Date: Fri, 06 Aug 2004 16:40:43 +0000
Hi R-users:
I've got a problem with lme.
In Rail data,I try to model the next one
lme(travel ~ Rail, data = Rail, random = ~ Rail | Rail)
I want travel = Rail(i) + Rail(j) + epsilon(i,j)
say, an effect fixed for every Rail and other for Rail(j) random, R says
fewer observations or false convergence.
Why can't I model an effect fixed and other random?
Thanks in advance.
My e-mail is [EMAIL PROTECTED]
Desc�rgalo y pru�balo 2 meses gratis.
______________________________________________
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
______________________________________________
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
______________________________________________
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
