matlib (version 0.9.8)

gsorth: Gram-Schmidt Orthogonalization of a Matrix

Description

Calculates a matrix with uncorrelated columns using the Gram-Schmidt process

Usage

gsorth(y, order, recenter = TRUE, rescale = TRUE, adjnames = TRUE)

Value

a matrix/data frame with uncorrelated columns

Arguments

y

a numeric matrix or data frame

order

if specified, a permutation of the column indices of y

recenter

logical; if TRUE, the result has same means as the original y, else means = 0 for cols 2:p

rescale

logical; if TRUE, the result has same sd as original, else, sd = residual sd

adjnames

logical; if TRUE, colnames are adjusted to Y1, Y2.1, Y3.12, ...

Details

This function, originally from the heplots package has now been deprecated in matlib. Use GramSchmidt instead.

Examples

if (FALSE) {
 set.seed(1234)
 A <- matrix(c(1:60 + rnorm(60)), 20, 3)
 cor(A)
 G <- gsorth(A)
 zapsmall(cor(G))
 }