wascores(x, w, expand=FALSE)
eigengrad(x, w)
wascores
returns a matrix where species define rows
and ordination axes or environmental variables define columns. If
expand = TRUE
, attribute shrinkage
has the inverses of
squared expansion factors or cca
eigenvalues for the
variable. Function eigengrad
returns only the shrinkage
attribute.wascores
computes weighted averages. Weighted averages
`shrink': they cannot be more extreme than values used for calculating
the averages. With expand = TRUE
, the function `dehsrinks' the
weighted averages by making their biased weighted variance equal to
the biased weighted variance of the corresponding environmental
variable. Function eigengrad
returns the inverses of squared
expansion factors or the attribute shrinkage
of the
wascores
result for each environmental gradient. This is equal
to the constrained eigenvalue of cca
when only this one
gradient was used as a constraint, and describes the strength of the
gradient.isoMDS
, cca
.data(varespec)
data(varechem)
library(MASS) ## isoMDS
vare.dist <- vegdist(wisconsin(varespec))
vare.mds <- isoMDS(vare.dist)
vare.points <- postMDS(vare.mds$points, vare.dist)
vare.wa <- wascores(vare.points, varespec)
plot(scores(vare.points), pch="+", asp=1)
text(vare.wa, rownames(vare.wa), cex=0.8, col="blue")
## Omit rare species (frequency <= 4)
freq <- apply(varespec>0, 2, sum)
plot(scores(vare.points), pch="+", asp=1)
text(vare.wa[freq > 4,], rownames(vare.wa)[freq > 4],cex=0.8,col="blue")
## Works for environmental variables, too.
wascores(varechem, varespec)
## And the strengths of these variables are:
eigengrad(varechem, varespec)
Run the code above in your browser using DataLab