Are you sure that Tukey's HSD (or any other usual multiple comparison
procedure) applies to within-subject factors?
I do not have my stats books (e.g. Winer or Kirk) to check.
You can get some output with:
TukeyHSD(aov(hand:gaze+subject))
(assuming you ant to compare the cells defined by hand:gaze)
but I am not sure wheter this is meaningful/correct in the context of the
within-subject design.
(Actually, I write this email because I am interested to know whether it is
a legitimate approach or not.)
Christophe
On 6/28/07, Patrick Bedard <Patrick_Bedard@brown.edu>
wrote:>
> Hello everyone,
>
> So I ran an anova with aov and then I want to run post-hoc comparisons but
> keep receiving this message :
> > no applicable method for "TukeyHSD"
>
> Here is my code:
>
> > d<-read.table("d.txt")
> > d
> > Obs subj Hand Gaze RT
> > 1 1 s1 1 1 401.4
> > 2 2 s2 1 1 363.3......
>
> > summary(ano <- aov(RT~(Hand*Gaze)+Error(subj/(Hand*Gaze)),data=d ))
>
>
> This seems to work fine, but then I use
> > fm1Tukey=TukeyHSD(fm1,"Hand") ; fm1Tukey
>
> And receive
> > no applicable method for "TukeyHSD"
>
>
> I can¹t seem to find the error nor anyone ever answering that question
> which
> seems to pop-up here and there on other websites (eg, Nabble)....
>
>
> Tnaks in advance for your help,
>
> __________________
> Patrick Bédard Ph.D.
> Dept. of Neuroscience
> Brown University
>
>
>
> [[alternative HTML version deleted]]
>
>
> ______________________________________________
> R-help@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.
>
>
--
Christophe Pallier (http://www.pallier.org)
[[alternative HTML version deleted]]