Information Technology Reference
In-Depth Information
correlation.biplot = FALSE, density.plot = FALSE,
ellipse.kappa = NULL, ellipse.alpha = NULL, exp.factor = 1.2,
factor.x = 2, factor.y = 2, font.3d = 2, ID.labs = FALSE,
ID.3d = 1:nrow(X), label = TRUE, label.size = 0.75,
large.scale = FALSE, legend.type = c(means = FALSE,
samples = FALSE, bags = FALSE), line.length = c(1,1),
line.size = 2.5, line.type = 1:ncol(G), line.width = 1,
markers = TRUE, marker.size = 0.6, max.num = 2500,
means.plot = FALSE, n.int = rep(5,sum(c(ncol(X),
ncol(X.new.vars)))), oblique.trans = NULL, offset = rep(0,4),
offset.m = rep(0.5,sum(c(ncol(X),ncol(X.new.vars)))),
ort.lty = 1, orthog.transx = rep(0,sum(c(ncol(X),
ncol(X.new.vars)))), orthog.transy = rep(0,sum(c(ncol(X),
ncol(X.new.vars)))), output = 1:10, parlegendmar = c(3,1,3,1),
parplotmar = rep(3,4), pch.means = 0:10, pch.means.size = 1,
pch.new = 1, pch.new.cols = "black", pch.new.labels = NULL,
pch.new.size = 0.75, pch.new.labels.size = 0.75,
pch.samples = 0:10, pch.samples.size = 1,
pos = c("Orthog","Hor","Paral"),
pos.m = rep(1,sum(c(ncol(X),ncol(X.new.vars)))),
predictions.3D = TRUE, predictions.mean = NULL,
predictions.sample = NULL, predictivity.print = FALSE,
quality.print = FALSE, reflect = c(FALSE,"x","y"),
rotate.degrees = 0, select.origin = FALSE,
side.label = rep("right",sum(c(ncol(X),ncol(X.new.vars)))),
size.ax.3d = 0.5, size.means.3d = 10, size.points.3d = 5,
specify.bags = NULL, specify.classes = dimnames(G)[[2]],
specify.ellipses = dimnames(G)[[2]], specify.xaxis = NULL,
text.width.mult = 1, Title = "",
Titles.3d = c("","","x","y","z"), Tukey.median = TRUE, ...)
Arguments
Required argument. Data matrix of size
n
×
p
representing
X
observations on
p
variables of
n
samples.
Optional argument. Indicator matrix defining
g
groups of
samples in the data.
G
Matrix of size
s
p
representing
s
new samples of
observations on the original
p
variables.
×
X.new.samples
Matrix of size
n
×
t
representing observations of the original
n
samples on
t
new variables.
X.new.vars
Logical argument indicating whether
X
is to be standardized to
unit column variances prior to performing the PCA.
Defaults to FALSE.
scaled.mat
Vector specifying the eigenvectors to be used for constructing
the scaffolding for the PCA biplot. Defaults to those
associated with the largest eigenvalues.
e.vects
Integer value of 1, 2 or 3 specifying the dimension of the PCA
biplot. Defaults to 2.
dim.biplot
