procrustes rotates a configuration to maximum similarity
with another configuration. Function protest tests the
non-randomness (`significance') between two configurations.
procrustes(X, Y, scale = TRUE, symmetric = FALSE, scores = "sites", ...)
"summary"(object, digits = getOption("digits"), ...)
"plot"(x, kind=1, choices=c(1,2), to.target = TRUE, type = "p", xlab, ylab, main, ar.col = "blue", len=0.05, cex = 0.7, ...)
"points"(x, display = c("target", "rotated"), choices = c(1,2), truemean = FALSE, ...)
"text"(x, display = c("target", "rotated"), choices = c(1,2), labels, truemean = FALSE, ...)
"lines"(x, type = c("segments", "arrows"), choices = c(1, 2), truemean = FALSE, ...)
"residuals"(object, ...)
"fitted"(object, truemean = TRUE, ...)
"predict"(object, newdata, truemean = TRUE, ...)
protest(X, Y, scores = "sites", permutations = how(nperm = 999), ...)Y.display argument
used with the corresponding scores function: see
scores, scores.cca and
scores.cca for alternatives.procrustes.plot function, the kind of plot produced:
kind = 1 plots shifts in two configurations, kind = 0
draws a corresponding empty plot, and kind = 2
plots an impulse diagram of residuals."target" or "rotated"
matrix as points.plot.procrustes needs
truemean = FALSE, and adding graphical items to the plots
from the original results may need truemean = TRUE.how, or the
number of permutations required, or a permutation matrix where each
row gives the permuted indices.procrustes
and protest parameters are passed to scores, in
graphical functions to underlying graphical functions.procrustes returns an object of class
procrustes with items. Function protest inherits from
procrustes, but amends that with some new items:scale=FALSE, the function only
rotates matrix Y. If scale=TRUE, it scales linearly
configuration Y for maximum similarity. Since Y is scaled
to fit X, the scaling is non-symmetric. However, with
symmetric=TRUE, the configurations are scaled to equal
dispersions and a symmetric version of the Procrustes statistic
is computed. Instead of matrix, X and Y can be results from an
ordination from which scores can extract results.
Function procrustes passes extra arguments to
scores, scores.cca etc. so that you can
specify arguments such as scaling.
Function plot plots a procrustes object and returns
invisibly an ordiplot object so that function
identify.ordiplot can be used for identifying
points. The items in the ordiplot object are called
heads and points with kind=1 (ordination
diagram) and sites with kind=2 (residuals). In
ordination diagrams, the arrow heads point to the target
configuration if to.target = TRUE, and to rotated
configuration if to.target = FALSE. Target and original
rotated axes are shown as cross hairs in two-dimensional Procrustes
analysis, and with a higher number of dimensions, the rotated axes
are projected onto plot with their scaled and centred
range. Function plot passes parameters to underlying plotting
functions. For full control of plots, you can draw the axes using
plot with kind = 0, and then add items with
points or lines. These functions pass all parameters
to the underlying functions so that you can select the plotting
characters, their size, colours etc., or you can select the width,
colour and type of line segments or arrows, or you can
select the orientation and head width of arrows.
Function residuals returns the pointwise
residuals, and fitted the fitted values, either centred to zero
mean (if truemean=FALSE) or with the original scale (these
hardly make sense if symmetric = TRUE). In
addition, there are summary and print methods.
If matrix X has a lower number of columns than matrix
Y, then matrix X will be filled with zero columns to
match dimensions. This means that the function can be used to rotate
an ordination configuration to an environmental variable (most
practically extracting the result with the fitted
function). Function predict can be used to add new rotated
coordinates to the target. The predict function will always
translate coordinates to the original non-centred matrix. The
function cannot be used with newdata for symmetric
analysis.
Function protest performs symmetric Procrustes analysis
repeatedly to estimate the `significance' of the Procrustes
statistic. Function protest uses a correlation-like statistic
derived from the symmetric Procrustes sum of squares $ss$ as
$r = sqrt(1-ss)$, and also prints the sum of
squares of the symmetric analysis, sometimes called
$squared m12$. Function protest has own
print method, but otherwise uses procrustes
methods. Thus plot with a protest object yields a
``Procrustean superimposition plot.''
Peres-Neto, P.R. and Jackson, D.A. (2001). How well do multivariate data sets match? The advantages of a Procrustean superimposition approach over the Mantel test. Oecologia 129: 169-178.
monoMDS, for obtaining
objects for procrustes, and mantel for an
alternative to protest without need of dimension reduction. See
how for details on specifying the type of
permutation required.data(varespec)
vare.dist <- vegdist(wisconsin(varespec))
mds.null <- monoMDS(vare.dist, y = cmdscale(vare.dist))
mds.alt <- monoMDS(vare.dist)
vare.proc <- procrustes(mds.alt, mds.null)
vare.proc
summary(vare.proc)
plot(vare.proc)
plot(vare.proc, kind=2)
residuals(vare.proc)
Run the code above in your browser using DataCamp Workspace