It seems your model defines more parameters then your data permits (e.g:
singular).
What you can do is try something like this:
summary(aov(formula('FP ~ (lum + obj + man)^2 - Error(vp/(lum + obj +
man)^2)),data=dataf))
(notice the use of + and ^)
This is something your data might permit (assuming this will answer
questions you are interested in answering)
Tal
----------------Contact
Details:-------------------------------------------------------
Contact me: Tal.Galili@gmail.com | 972-52-7275845
Read me: www.talgalili.com (Hebrew) | www.biostatistics.co.il (Hebrew) |
www.r-statistics.com (English)
----------------------------------------------------------------------------------------------
On Tue, Nov 23, 2010 at 4:58 PM, Marius 't Hart <M.t.Hart@ai.rug.nl>
wrote:
> Hi all,
>
> I'm doing a 3-way ANOVA like this:
>
> summary(aov(formula('FP ~ (lum * obj * man)3 - Error(vp/(lum * obj *
> man)3)'),data=dataf))
>
> But in the output I only get 1- and 2-way effects, like this one:
>
> Error: vp:obj:man
> Df Sum Sq Mean Sq F value Pr(>F)
> obj:man 1 1.5291e-34 1.5291e-34 5.7011 0.0542 .
> Residuals 6 1.6093e-34 2.6822e-35
> ---
> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05
'.' 0.1 ' ' 1
>
> (And a warning that the Error() model is singular.)
>
> What am I doing wrong so that I don't get the 3-way interactions I want
> to look at?
>
> Thank you!
>
> Marius.
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org 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.
>
[[alternative HTML version deleted]]