Plotting Correspondence Regression

Share:

Description

Basic method to plot the output of a correspondence regression.

Usage

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
## S3 method for class 'corregp'
plot(x, axes = 1:2, y_btm = TRUE, y_ell = FALSE,
  x_ell = FALSE, ysub = NULL, xsub = NULL, hlim = NULL, vlim = NULL,
  expa_btm = 1, expa_top = 1, asp = 1, asp_btm = asp, asp_top = asp,
  col_btm = "darkgrey", col_top = "red", cex_btm = par("cex"),
  cex_top = cex_btm, font_btm = par("font"), font_top = font_btm,
  col_ell = par("col"), lwd_ell = par("lwd"), lty_ell = par("lty"),
  col_ori = par("col"), lwd_ori = par("lwd"), lty_ori = 1, main = NULL,
  sub = NULL, hlab = NULL, vlab = NULL, cl = 0.95, np = 100,
  add_ori = TRUE, ...)

Arguments

x

The output of a call to corregp (i.e. an object of class "corregp").

axes

The axes to plot: a vector of two values. Defaults to the first two axes.

y_btm

Logical specifying whether the Y levels should be plotted first ("at the bottom") and then be overlaid by the X levels. Defaults to TRUE.

y_ell

Logical specifying whether the confidence ellipses of the Y levels should be plotted. Defaults to FALSE.

x_ell

Logical specifying whether the confidence ellipses of the X levels should be plotted. Defaults to FALSE.

ysub

Vector of indices to select a subset of the Y levels.

xsub

Vector of indices to select a subset of the X levels.

hlim

Vector of two values specifying the lower and upper limit between which to plot the horizontal axis.

vlim

Vector of two values specifying the lower and upper limit between which to plot the vertical axis.

expa_btm

Expansion factor for the bottom coordinates: a number to rescale the axes.

expa_top

Expansion factor for the top coordinates: a number to rescale the axes.

asp

The aspect ratio for the whole plot. See plot.window.

asp_btm

The aspect ratio for the bottom coordinates. See plot.window.

asp_top

The aspect ratio for the top coordinates. See plot.window.

col_btm

Color of the bottom levels: either numeric or see colors. Defaults to "darkgrey".

col_top

Color of the top levels: either numeric or see colors. Defaults to "red".

cex_btm

Character expansion factor of the bottom levels: a number to specify the size of the text labels.

cex_top

Character expansion factor of the top levels: a number to specify the size of the text labels.

font_btm

Font of the bottom levels: 1 for plain, 2 for bold, 3 for italic, and 4 for bold italic. Defaults to 1.

font_top

Font of the top levels: 1 for plain, 2 for bold, 3 for italic, and 4 for bold italic. Defaults to 1.

col_ell

Color of the confidence ellipses: either a number or see colors.

lwd_ell

Width of the confidence ellipses: a number to specify the line width.

lty_ell

Line type of the confidence ellipses: 0 or "blank", 1 or "solid", 2 or "dashed", 3 or "dotted", 4 or "dotdash", 5 or "longdash", 6 or "twodash". Defaults to 1.

col_ori

Color of the lines through the origin: either numeric or see colors.

lwd_ori

Width of the lines through the origin: a number to specify the line width.

lty_ori

Line type of the lines through the origin: 0 or "blank", 1 or "solid", 2 or "dashed", 3 or "dotted", 4 or "dotdash", 5 or "longdash", 6 or "twodash". Defaults to 1.

main

The main title of the plot.

sub

The subtitle of the plot.

hlab

The title of the horizontal axis.

vlab

The title of the vertical axis.

cl

The confidence level for the confidence ellipses. Defaults to 0.95.

np

The number of points to represent the confidence ellipses. Defaults to 100.

add_ori

Logical specifying whether to add lines through the origin. Defaults to TRUE.

...

Further arguments passed to or from other methods.

Details

The plot of a correspondence regression is by definition a biplot.

Value

A plot window containing the output of a correspondence regression.

References

Gower, J., S. Lubbe and N. Le Roux (2011) Understanding biplots. Chichester: Wiley.

Greenacre, M. (2010) Biplots in practice. Bilbao: Fundacion BBVA.

See Also

corregp, summary.corregp, screeplot.corregp, biplot.

Examples

1
2
3
data(HairEye)
haireye.crg <- corregp(Eye ~ Hair * Sex, data = HairEye, b = 3000)
plot(haireye.crg, x_ell = TRUE, xsub = c("Hair", "Sex"))