Learn R Programming

depth (version 2.0-0)

scontour: Plotting spherical depth contours

Description

Traces spherical depth contours of a multivariate data set. Supports data on the circle or on the sphere.

Usage

scontour(P, tracepoints=FALSE, colpoints="black", tracemed=TRUE, maxdepth=FALSE, xlim=c(0,2*pi), displaymed=FALSE, title="Circular Tukey contours", ylab="Tukey's circular depth", xlab=expression(theta), colmed=2, colarc="red", sizepoints=3)

Arguments

P
The data as a vector, a matrix, a data frame or a list.
tracepoints
Logical; if TRUE, data points are added to the plot.
colpoints
A specification for the color of the data points.
tracemed
Logical; if TRUE, the Tukey median is added to the plot.
maxdepth
Logical; On the circle only; if TRUE, the maximum depth is printed on the plot.
xlim
Numeric vectors of length 2, giving the x coordinate range.
displaymed
Logical; On the circle only; if TRUE, the median value is printed on the plot.
title
On the circle only, a specification for the plot title.
ylab
On the circle only, a specification for the y axis title.
xlab
On the circle only, a specification for the x axis title.
colmed
Color of the Tukey median on the plot.
colarc
On the sphere only, color of the spherical depth contours on the plot.
sizepoints
Size of plotted points.

Value

plot
A plot of Tukey spherical depth if the input data are on the circle, or the Tukey spherical depth contours if the input data are on the sphere.
If data are on the sphere only, a list of 3 elements is also outputted.
1
A sorted vector giving the depths of the plotted contours.
2
A list of matrices with the vertices of every contour.
3
The Euclidean coordinates of the Tukey median

Details

Supports data on the circle or the sphere. For data on the circle, data must be expressed in polar coordinates as a angle in radians with values between 0 and $2\pi$. Data on the sphere can be expressed in Euclidean coordinates ($n$ by 3 matrix) or in spherical coordinates ($n$ by 2 matrix) where the first column contains $\theta$ and the second column $\phi$. The type of coordinates is determined automatically based on the dimensions of the input.

References

Liu, R.Y., Parelius, J.M. and Singh, K. (1999), Multivariate analysis by data depth: Descriptive statistics, graphics and inference (with discussion), Ann. Statist., 27, 783--858.

Mardia, K.V. and Jupp, E.J. (1999). Directional Statistics, Wiley.

See Also

sdepth for calculation of the depth of a point, smed for Tukey's spherical median.

Examples

Run this code
set.seed(2011)
scontour(runif(30,min=0,max=2*pi))

## Tukey spherical depth contours for data 
## on the shpere expressed in spherical coordinates.
scontour(cbind(runif(20,min=0,max=2*pi),runif(20,min=0,max=pi)))

## Tukey spherical depth contours for data 
## on the sphere expressed in Euclidean coordinates.
x=matrix(rnorm(60),ncol=3)
x=t(apply(x,1,function(y){y/sqrt(sum(y^2))}))
scontour(x)

Run the code above in your browser using DataLab