ternaryplot: Ternary diagram

Description

Visualizes compositional, 3-dimensional data in an equilateral triangle (from the vcd library, Version 0.1-3.3, Date 2004-04-21), using plot graphics. Differs from implementation in vcd (0.9-7), which uses grid graphics.

Usage

ternaryplot(x, scale = 1, dimnames = NULL, dimnames.position = c("corner","edge","none"),
            dimnames.color = "black", id = NULL, id.color = "black", coordinates = FALSE,
	    grid = TRUE, grid.color = "gray", labels = c("inside", "outside", "none"),
	    labels.color = "darkgray", border = "black", bg = "white", pch = 19, cex = 1,
	    prop.size = FALSE, col = "red", main = "ternary plot", ...)

Arguments

a matrix with three columns.

scale

row sums scale to be used.

dimnames

dimension labels (defaults to the column names of x).

dimnames.position, dimnames.color

position and color of dimension labels.

optional labels to be plotted below the plot symbols. coordinates and id are mutual exclusive.

id.color

color of these labels.

coordinates

if TRUE, the coordinates of the points are plotted below them. coordinates and id are mutual exclusive.

grid

if TRUE, a grid is plotted. May optionally be a string indicating the line type (default: "dotted").

grid.color

grid color.

labels, labels.color

position and color of the grid labels.

border

color of the triangle border.

triangle background.

pch

plotting character. Defaults to filled dots.

cex

a numerical value giving the amount by which plotting text and symbols should be scaled relative to the default. Ignored for the symbol size if prop.size is not FALSE.

prop.size

if TRUE, the symbol size is plotted proportional to the row sum of the three variables, i.e. represents the weight of the observation.

col

plotting color.

main

main title.

...

additional graphics parameters (see par)

Details

A points' coordinates are found by computing the gravity center of mass points using the data entries as weights. Thus, the coordinates of a point P(a,b,c), $a + b + c = 1$, are: P(b + c/2, c * sqrt(3)/2).

References

M. Friendly (2000), Visualizing Categorical Data. SAS Institute, Cary, NC.

Examples

Run this code

data(mexico)
if (require(VGAM)) { 
z.out <- zelig(as.factor(vote88) ~ pristr + othcok + othsocok, 
                model = "mlogit", data = mexico)
x.out <- setx(z.out)
s.out <- sim(z.out, x = x.out)

ternaryplot(s.out$qi$ev, pch = ".", col = "blue",
            main = "1988 Mexican Presidential Election")
}