repeated measures with multivariate data
Interesting that you ask; I was currently thinking about the same thing. Once a reviewer required us to do a Doubly Repeated Measures ANOVA "Doubly because the multiple variables and the repeated measures parts are both multivariate dimensions." At the time, I did not find how to do it in R, and was wondering just this week if something similar could be done using a mixed model... Abra?os, Rafael Maia --- "A little learning is a dangerous thing; drink deep, or taste not the Pierian spring." (A. Pope) Graduate Student - Integrated Bioscience University of Akron http://gozips.uakron.edu/~shawkey/
On Jul 23, 2010, at 7:08 PM, Peter Solymos wrote:
Kay,
using strata (restricting permutations within time points, and not
within locations) in adonis makes some sense, given that permutation
tests assume independence. But that does not solve the problem of
dependence, but it is a good starter. If you have a before-after
control-treatment design, you might want to use the absolute
difference between observations and do the adonis on the matrix of
differences (the dissimilarity then will represent distance in terms
of absolute deviation between time points). However, this won't show
the sign of the change, which might be of interest. If you have larger
number of repeated observations, the MARSS package is just appeared on
CRAN to fit multivariate autoregressive state-space models using a
Kalman-filter approach.
Cheers,
Peter
P?ter S?lymos
Alberta Biodiversity Monitoring Institute
and Boreal Avian Modelling project
Department of Biological Sciences
CW 405, Biological Sciences Bldg
University of Alberta
Edmonton, Alberta, T6G 2E9, Canada
Phone: 780.492.8534
Fax: 780.492.7635
email <- paste("solymos", "ualberta.ca", sep = "@")
http://www.abmi.ca
http://sites.google.com/site/psolymos
On Fri, Jul 23, 2010 at 1:02 PM, Kay Cichini <Kay.Cichini at uibk.ac.at> wrote:
dear list, i searched though the archives and the question of repeated measure analysis with species data was often brought up but, as far as i found, never clearly worked out. if i have, say two time points at wich i sampled replicated plots and thus had replicated paired mutivariate obervations, how to deal with them properly. if i used adonis, to restrict permutations on the pairs of plots (as this would be done in an univariate permutation test for paired observations) does not make sense to me but i'm also dubious about neglecting the dependence of the pairing. any ideas would be highly appreciated, kay ----- ------------------------ Kay Cichini Postgraduate student Institute of Botany Univ. of Innsbruck ------------------------ -- View this message in context: http://r-sig-ecology.471788.n2.nabble.com/repeated-measures-with-multivariate-data-tp5330819p5330819.html Sent from the r-sig-ecology mailing list archive at Nabble.com.
_______________________________________________ R-sig-ecology mailing list R-sig-ecology at r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
_______________________________________________ R-sig-ecology mailing list R-sig-ecology at r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-ecology