Hey Folks,

I am new to R and am trying to modify my multivariate eco-statistics course
by giving my students the option of doing all of the assignments in R.

One of the exercises I've been doing in Primer, but would like to do in R,
is a repeated measures permutation MANOVA, wherein I examine how plant
species composition responds to a restoration treatment over time. The
experimental design is pretty simple: a CRD with 10 treated plots and 10
control plots (each plot is considered equivalent to a random "subject")
with composition measured in two different years, similar to a simple BACI
study, except that I have two "after" censuses (1 year after the treatment
was initiated and 3 years after the treatment was initiated) and no "before"
census of the vegetation.

I thought I might be able to do this using adonis and the "strata" argument,
but it is not clear to me how to nest "plot" within treatment but not within
year so that the treatment effect is tested with "between-subjects" error
while year and its interaction with treatment are tested with
"within-subjects" error.

I'm happy to provide more details if necessary.

Thanks,
Steve


J. Stephen Brewer 
Professor 
Department of Biology
PO Box 1848
 University of Mississippi
University, Mississippi 38677-1848
 Brewer web page - http://home.olemiss.edu/~jbrewer/
FAX - 662-915-5144 Phone - 662-915-1077



        [[alternative HTML version deleted]]

_______________________________________________
R-sig-ecology mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology

Reply via email to