hdrcde (version 2.15)

hdr.boxplot.2d: Bivariate Highest Density Regions

Description

Calculates and plots highest density regions in two dimensions, including the bivariate HDR boxplot.

Usage

hdr.boxplot.2d(x, y, prob=c(0.01,0.50), h, show.points = FALSE, 
    xlab="", ylab="",  kde.package=c("ash","ks"), shadecols, pointcol, xextend=0.15, yextend=0.15, ...)

Arguments

x

Numeric vector

y

Numeric vector of same length as x.

prob

Probability coverage required for HDRs

h

Pair of bandwidths passed to either ash2 or kde. If missing, a reasonable default is used.

show.points

If TRUE, will plot points over the top of contours.

xlab

Label for x-axis.

ylab

Label for y-axis.

kde.package

Package to be used in calculating the kernel density estimate.

shadecols

Colors for shaded regions

pointcol

Color for outliers and mode

xextend

Proportion of range of x. The density is estimated on a grid extended by xextend beyond the range of x.

yextend

Proportion of range of y. The density is estimated on a grid extended by yextend beyond the range of y.

...

Other arguments to be passed to plot.

Value

• Some information about the HDRs is returned. See code for details.

Details

The density is estimated using kernel density estimation. Either ash2 or kde is used to do the calculations. Then Hyndman's (1996) density quantile algorithm is used to compute the HDRs.

References

Hyndman, R.J. (1996) Computing and graphing highest density regions American Statistician, 50, 120-126.

See Also

hdr.boxplot

Examples

x <- c(rnorm(200,0,1),rnorm(200,4,1))
y <- c(rnorm(200,0,1),rnorm(200,4,1))
par(mfrow=c(1,2))
plot(x,y)
hdr.boxplot.2d(x,y)