rotate2d {ecodist} | R Documentation |
Rotates a two-dimensional ordination configuration to place the direction indicated along the horizontal axis.
rotate2d(ord, x)
ord |
A matrix or data frame with two columns, or a vf object, containing the points of an ordination configuration. |
x |
The coordinates of a point in the ordination space. |
The configuration ord is rotated so that the vector defined by c(0, 0), and x is along the horizontal axis. This can be useful for placing a specific variable, for instance from vf(), in a consistent direction across multiple ordinations. Doing so can facilitate interpretation.
A rotated data frame of coordinates of the same size as ord and in the same order. If ord was produced by vf(), the complete vf object is returned.
Sarah Goslee
# Example of multivariate analysis using built-in iris dataset
data(iris)
iris.d <- dist(iris[,1:4])
### nmds() is timeconsuming, so this was generated
### in advance and saved.
### set.seed(1234)
### iris.nmds <- nmds(iris.d, nits=20, mindim=1, maxdim=4)
### save(iris.nmds, file="ecodist/data/iris.nmds.rda")
data(iris.nmds)
# examine fit by number of dimensions
plot(iris.nmds)
# choose the best two-dimensional solution to work with
iris.nmin <- min(iris.nmds, dims=2)
# fit the data to the ordination as vectors
### vf() is timeconsuming, so this was generated
### in advance and saved.
### set.seed(1234)
### iris.vf <- vf(iris.nmin, iris[,1:4], nperm=1000)
### save(iris.vf, file="ecodist/data/iris.vf.rda")
data(iris.vf)
plot(iris.nmin, col=as.numeric(iris$Species), pch=as.numeric(iris$Species), main="NMDS")
plot(iris.vf)
# rotate configuration so Sepal Width is along the horizontal axis
iris.nmin.rot <- rotate2d(iris.nmin, iris.vf[2, 1:2])
iris.vf.rot <- rotate2d(iris.vf, iris.vf[2, 1:2])
plot(iris.nmin.rot, col=as.numeric(iris$Species), pch=as.numeric(iris$Species), main="NMDS")
plot(iris.vf.rot)