PP3 (version 1.2)

PP3init: Initialize projection pursuit code

Description

Initialize projection pursuit code. This function only need be executed once. Then subsequent calls to projection index calculation can reuse the results of this initialization many times.

Usage

PP3init(xm, action = 0, limit = 3)

Arguments

xm

Data matrix containing K rows (variables) and N columns (observations).

action

Possible outlier action. See help to PP3many for description.

limit

Possible outlier action. See help to PP3many for description.

Value

A list with the following components.

COPYN

An integer less than or equal to the number of columns of the input matrix. The number of points that were kept after outlier processing (for index computation only).

ansT

The three-dimensional T summary statistic array

ansU

The four-dimensional U summary statistic array

Details

This function spheres the data and calculates third- and fourth-order moment quantities, which can be used for subsequent index calculation.

References

Friedman, J.H. and Tukey, J.W. (1974) A projection pursuit algorithm for exploratory data analysis. IEEE Trans. Comput., 23, 881-890.

Jones, M.C. and Sibson, R. (1987) What is projection pursuit? (with discussion) J. R. Statist. Soc. A, 150, 1-36.

Nason, G. P. (1995) Three-dimensional projection pursuit. J. R. Statist. Soc. C, 44, 411-430.

Nason, G. P. (2001) Robust projection indices. J. R. Statist. Soc. B, 63, 551-567.

See Also

PP3many

Examples

# NOT RUN {
#
# Not designed for direct user use, but here is an example
#
#
# The flea beetle data
#
data(beetle)
#
# Initialise the PP3 system for this data
#
tmp <- PP3init(t(beetle))
#
# This object contains the ansT and ansU third- and fourth-order tensors
#
# }