Marcelo Martinez Palao <marmp at fcu.um.es> writes:
I'm working with a orthogonal and nested model (mixed). I have four factors, A,B,C,D; A and B are fixed and orthogonal C is nested in AB interaction and finally, D is nested in C. I would like to model the following Y_ijklm=Mu+A_i+B_j+AB_ij+C_k(ij)+D_l(k(ij))+Error_m(...) I used the next command
summary(aov(abund~A*B + C % in % A:B + D % in % C % in % A:B ,datos))
Is it the correct formula syntax?
I would recommend using the lme (linear mixed-effects) function from
the nlme package for this. Please ensure that you have R version
0.90.0 installed, then use
install.packages("nlme")
from within R to obtain and install the package.
If I understand your message correctly, your model specification would be
fm1 <- lme(abund ~ A * B, random = list(C = ~ 1, D = ~ 1), data = datos)
This will fit the restricted maximum likelihood (REML) estimates.
If you prefer to get maximum likelihood (ML) estimates, include the argument
method = "ML"
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._