Cross-Mantel test
Simple and partial cross-Mantel tests, with options for ranked data and permutation tests.
xmantel(formula = formula(data), data, dims = NA, nperm = 1000, mrank = FALSE)
formula |
formula describing the test to be conducted. For this test, y ~ x will perform a simple Mantel test, while y ~ x + z1 + z2 + z3 will do a partial Mantel test of the relationship between x and y given z1, z2, z3. All variables should be either non-symmetric square cross-dissimilary matrices of class xdist, or vector forms thereof. |
data |
an optional dataframe containing the variables in the model as columns of dissimilarities. By default the variables are taken from the current environment. |
dims |
if the dissimilarity matrices are not square, the dimensions must be provided as |
nperm |
number of permutations to use. If set to 0, the permutation test will be omitted. |
mrank |
if this is set to FALSE (the default option), Pearson correlations will be used. If set to TRUE, the Spearman correlation (correlation ranked distances) will be used. |
If only one independent variable is given, the simple Mantel r (r12) is calculated. If more than one independent variable is given, the partial Mantel r (ryx|x1 ...) is calculated by permuting one of the original dissimilarity matrices. Note that the cross-dissimilarity functions are for research purposes, and are not well-tested.
mantelr |
Mantel coefficient. |
pval1 |
one-tailed p-value (null hypothesis: r <= 0). |
pval2 |
one-tailed p-value (null hypothesis: r >= 0). |
pval3 |
two-tailed p-value (null hypothesis: r = 0). |
Sarah Goslee
data(graze)
### EXAMPLE 1: Square matrices
# take two subsets of sites with different dominant grass abundances
# use cut-offs that produce equal numbers of sites
dom1 <- subset(graze, POPR > 50 & DAGL < 20) # 8 sites
dom2 <- subset(graze, POPR < 50 & DAGL > 20) # 8 sites
# first two columns are site info
dom.xd <- xdistance(dom1[, -c(1,2)], dom2[, -c(1,2)], "bray")
# environmental and spatial distances; preserve rownames
forest.xd <- xdistance(dom1[, "forestpct", drop=FALSE],
dom2[, "forestpct", drop=FALSE])
sitelocation.xd <- xdistance(dom1[, "sitelocation", drop=FALSE],
dom2[, "sitelocation", drop=FALSE])
# permutes rows and columns of full nonsymmetric matrix
xmantel(dom.xd ~ forest.xd)
xmantel(dom.xd ~ forest.xd + sitelocation.xd)
plot(xmgram(dom.xd, sitelocation.xd))
### EXAMPLE 2: Non-square matrices
# take two subsets of sites with different dominant grass abundances
# this produces a non-square matrix
dom1 <- subset(graze, POPR > 45 & DAGL < 20) # 13 sites
dom2 <- subset(graze, POPR < 45 & DAGL > 20) # 8 sites
# first two columns are site info
dom.xd <- xdistance(dom1[, -c(1,2)], dom2[, -c(1,2)], "bray")
# environmental and spatial distances; preserve rownames
forest.xd <- xdistance(dom1[, "forestpct", drop=FALSE],
dom2[, "forestpct", drop=FALSE])
sitelocation.xd <- xdistance(dom1[, "sitelocation", drop=FALSE],
dom2[, "sitelocation", drop=FALSE])
# permutes rows and columns of full nonsymmetric matrix
xmantel(dom.xd ~ forest.xd, dims=c(13, 8))
xmantel(dom.xd ~ forest.xd + sitelocation.xd, dims=c(13, 8))
plot(xmgram(dom.xd, sitelocation.xd))Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.