stressplot.wcmdscale: Display Ordination Distances Against Observed Distances in...

Description Usage Arguments Details Value Author(s) See Also Examples

Description

Functions plot ordination distances in given number of dimensions against observed distances or distances in full space in eigenvector methods. The display is similar as the Shepard diagram (stressplot for non-metric multidimensional scaling with metaMDS or monoMDS), but shows the linear relationship of the eigenvector ordinations. The stressplot methods are available for wcmdscale, rda, cca, capscale, prcomp and princomp.

Usage

1
2
3
## S3 method for class 'wcmdscale'
stressplot(object, k = 2, pch, p.col = "blue", l.col = "red",
    lwd = 2, ...)

Arguments

object

Result object from eigenvector ordination (wcmdscale, rda, cca, capscale)

k

Number of dimensions for which the ordination distances are displayed.

pch, p.col, l.col, lwd

Plotting character, point colour and line colour like in default stressplot

...

Other parameters to functions, e.g. graphical parameters.

Details

The functions offer a similar display for eigenvector ordinations as the standard Shepard diagram (stressplot) in non-metric multidimensional scaling. The ordination distances in given number of dimensions are plotted against observed distances. With metric distances, the ordination distances in full space (with all ordination axes) are equal to observed distances, and the fit line shows this equality. In general, the fit line does not go through the points, but the points for observed distances approach the fit line from below. However, with non-metric distances (in wcmdscale or capscale) with negative eigenvalues the ordination distances can exceed the observed distances in real dimensions; the imaginary dimensions with negative eigenvalues will correct these excess distances. If you have used capscale with argument add = TRUE to avoid negative eigenvalues, the ordination distances will exceed the observed dissimilarities by the additive constant.

In partial ordination (cca, rda and capscale with Condition in the formula), the distances in the partial component are included both in the observed distances and in ordination distances. With k=0, the ordination distances refer to the partial ordination.

Value

Functions draw a graph and return invisibly the ordination distances.

Author(s)

Jari Oksanen.

See Also

stressplot and stressplot.monoMDS for standard Shepard diagrams.

Examples

1
2
3
4
5
data(dune, dune.env)
mod <- rda(dune)
stressplot(mod)
mod <- rda(dune ~ Management, dune.env)
stressplot(mod, k=3)

Example output

Loading required package: permute
Loading required package: lattice
This is vegan 2.4-4

vegan documentation built on May 2, 2019, 5:51 p.m.