heplots (version 1.1-0)

covEllipses: Draw classical and robust covariance ellipses for one or more groups

Description

The function draws covariance ellipses for one or more groups and optionally for the pooled total sample. It uses either the classical product-moment covariance estimate, or a robust alternative, as provided by cov.rob.

Usage

covEllipses(x, ...)

## S3 method for class 'boxM':
covEllipses(x, ...)

## S3 method for class 'data.frame':
covEllipses(x, group, pooled = TRUE, method = c("classical", "mve", "mcd"), ...)

## S3 method for class 'matrix':
covEllipses(x, group, pooled = TRUE, method = c("classical", "mve", "mcd"), ...)

## S3 method for class 'default':
covEllipses(x, means, df, 
        labels = NULL, variables = 1:2, level = 0.68, 
        segments = 40, 
        center = FALSE, center.pch = "+", center.cex = 2, 
        col = getOption("heplot.colors", c("red", "blue", "black", "darkgreen", 
                        "darkcyan", "magenta", "brown", "darkgray")), 
        lty = 1, lwd = 2, 
        fill = FALSE, fill.alpha = 0.3, 
        label.pos = 0, 
        xlab, ylab, main = "", 
        xlim, ylim, axes = TRUE, 
        offset.axes, add = FALSE, warn.rank = FALSE, ...)

Arguments

x

The generic argument. For the default method, this is a list of covariance matrices. For the data.frame and matrix methods, this is a numeric matrix of two or more columns.

group

a factor defining groups, or a vector of length n=nrow(x) doing the same. If missing, a single covariance ellipse is drawn.

pooled

Logical; if TRUE, the pooled covariance matrix is also computed and plotted

method

the covariance method to be used: classical product-moment ("classical"), or minimum volume ellipsoid ("mve"), or minimum covariance determinant ("mcd").

means

For the default method, a matrix of the means for all groups (followed by the grand means, if pooled=TRUE). Rows are the groups, and columns are the variables. It is assumed that the means have column names corresponding to the variables in

df

For the default method, a vector of the degrees of freedom for the covariance matrices

labels

Either a character vector of labels for the groups, or TRUE, indicating that group labels are taken as the names of the covariance matrices. Use labels="" to suppress group labels

variables

indices or names of the two response variables to be plotted; defaults to 1:2.

level

equivalent coverage of ellipse for normally-distributed errors, defaults to 0.68.

segments

number of line segments composing each ellipse; defaults to 40.

center

If TRUE, the covariance ellipses are centered at the centroid.

center.pch

character to use in plotting the centroid of the data; defaults to "+".

center.cex

size of character to use in plotting the centroid of the data; defaults to 2.

col

a color or vector of colors to use in plotting ellipses --- recycled as necessary A single color can be given, in which case it is used for all ellipses. For convenience, the default colors for all plots produced in a given session can be c

lty

vector of line types to use for plotting the ellipses; the first is used for the error ellipse, the rest --- possibly recycled --- for the hypothesis ellipses; a single line type can be given. Defaults to 2:1.

lwd

vector of line widths to use for plotting the ellipses; the first is used for the error ellipse, the rest --- possibly recycled --- for the hypothesis ellipses; a single line width can be given. Defaults to 1:2.

fill

A logical vector indicating whether each ellipse should be filled or not. The first value is used for the error ellipse, the rest --- possibly recycled --- for the hypothesis ellipses; a single fill value can be given. Defaults to FALSE f

fill.alpha

Alpha transparency for filled ellipses, a numeric scalar or vector of values within [0,1], where 0 means fully transparent and 1 means fully opaque. Defaults to 0.3.

label.pos

Label position, a vector of integers (in 0:4) or character strings (in c("center", "bottom", "left", "top", "right")) use in labeling ellipses, recycled as necessary. Values of 1, 2, 3 and 4, respectively indicate positions

xlab

x-axis label; defaults to name of the x variable.

ylab

y-axis label; defaults to name of the y variable.

main

main plot label; defaults to "".

xlim

x-axis limits; if absent, will be computed from the data.

ylim

y-axis limits; if absent, will be computed from the data.

axes

Whether to draw the x, y axes; defaults to TRUE

offset.axes

proportion to extend the axes in each direction if computed from the data; optional.

add

if TRUE, add to the current plot; the default is FALSE.

warn.rank

if TRUE, do not suppress warnings about the rank of the covariance matrices; the default is FALSE.

...

Other arguments passed to the default method for plot, text, and points

Value

• Returns invisibly an object of class "covEllipse", which is a list of the coordinates for the ellipses drawn.

Details

This plot method provides one way to visualize possible heterogeneity of covariance matrices in a one-way MANOVA design.

See Also

heplot, boxM, cov.rob

Examples

data(iris)

covEllipses(iris[,1:4], iris$Species)
covEllipses(iris[,1:4], iris$Species, fill=TRUE, method="mve", add=TRUE, labels="")
	
x <- boxM(iris[, 1:4], iris[, "Species"])
x
covEllipses(x, fill=c(rep(FALSE,3), TRUE) )
covEllipses(x, fill=c(rep(FALSE,3), TRUE), center=TRUE, label.pos=1:4 )

cov <- c(x$cov, pooled=list(x$pooled))
df <- c(table(iris$Species)-1, nrow(iris)-3)
covEllipses(cov, x$means, df, label.pos=3, fill=c(rep(FALSE,3), TRUE))
 
covEllipses(cov, x$means, df, label.pos=3, fill=c(rep(FALSE,3), TRUE), center=TRUE)