Have you considered the 'lme' function in library(nlme)? The
'lme'
function is new, much more flexible, and as far as I know at least as
good and usually better than 'aov'. I would try the following:
fit <- lme(response~CO2*NITROGEN, random=~1|ROOM)
Checking "methods(class='lme')" gives a list of helper
functions to
do a variety of useful things with 'fit'. For more information, see
Pinheiro and Bates (2000) Mixed-Effects Models in S and S-Plus
(Springer). I suggest you use the companion R script files in the
"~\library\nlme\scripts" subdirectory of your R installation to
facilitate your study of the book. There is at least one minor but
important difference in the syntax between the book and R. In addition,
using these script files should save you from any problems with
typographical errors, thereby making your study more enjoyable and
educational.
Hope this helps.
Spencer Graves
Chreis Habeck wrote:> How do I set up my model equation in aov to analyze a split-plot design?
>
> I have two factors (CO2 and NITROGEN), each with two levels (high and
> ambient). CO2 is my whole-plot factor with three replicates for each
level
> (i.e., 6 rooms total).
>
> Is this syntax below correct?
>
> summary(aov(response ~ ROOM + CO2*NITROGEN + Error(ROOM/CO2)))
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.