msr.4thcorner {adespatial} | R Documentation |
This function allows to test fourth-corner statistics using constrained null
models (for traits and/or environmental variables). If the argument
phyloORorthobasis
is specified, random traits are
phylogenetically-constrained to preserve the global autocorrelation (Moran's
I) and the phylogenetic structures at multiple scales. If not, standard
permutations are used. If the argument listwORorthobasis
is specified,
random environmental variables are spatially-constrained to preserve the
global autocorrelation (Moran's I) and the spatial structures at multiple
scales. If not, standard permutations are used. Multiscale property is
defined by the power spectrum (i.e. decomposition of the variance of the
original variables) on a basis of orthonormal eigenvectors (Moran's
Eigenvector Maps, MEM).
## S3 method for class ''4thcorner'' msr( x, listwORorthobasis, phyloORorthobasis, nrepet = x$npermut, method = c("pair", "triplet", "singleton"), ... )
x |
An object generated by the |
listwORorthobasis |
an object of the class |
phyloORorthobasis |
an object of the class |
nrepet |
an |
method |
an character specifying which algorithm should be used to produce spatial replicates (see codemsr.default). |
... |
further arguments of the codemsr.default function. |
An object of class 4thcorner
randomized replicates.
Stephane Dray stephane.dray@univ-lyon1.fr
Braga, J., Thuiller, W., ter Braak, C.J.F. and Dray, S. (2018) Integrating spatial and phylogenetic information in the fourth-corner analysis to test trait-environment relationships. Ecology, 99:2667-2674.
if(require("ade4", quietly = TRUE) & require("adephylo", quietly = TRUE) & require("spdep", quietly = TRUE) & require("ape", quietly = TRUE)){ data(mafragh, package = "ade4") fr1 <- fourthcorner(mafragh$env, mafragh$flo, mafragh$traits$tabQuantitative, nrepet = 49) phy <- read.tree(text = mafragh$tre) lw <- nb2listw(mafragh$nb) fr1.msr <- msr(fr1, listwORorthobasis = lw, phyloORorthobasis = phy) fr1 fr1.msr }