[R-sig-ME] Conducting an anova with multiple error terms

[Emma Stone]

Dear All,

I am conducting an anova with multiple error terms:

model<-aov(time~treat+Error(site/treat))

and would like to be able to do post hoc tests (eg Tukeys) but the aov
function only allows Tukeys test with aov.objects and the aov with multiple
error terms creates and aov.list.

Can anyone suggest a solution to this?

previous posts on the forum have stated that I can use the following code
with the glht function, but this also only works on aov. objects.

summary(glht(model, linfct=mcp(V="Tukey")))

Any ideas would be very much appreciated!!
----------------------
Emma Stone
Postgraduate Researcher
Bat Ecology and Bioacoustics Lab
& Mammal Research Unit
School of Biological Sciences,
University of Bristol, Woodland Road,
Bristol, BS8 1UG
Email: emma.stone at bristol.ac.uk