WMDB (version 1.0)

wmahalanobis: Compute weighted Mahalanobis distance

Description

compute weighted Mahalanobis distance between two samples

Usage

wmahalanobis(x, center, cov, weight)

Arguments

x

vector or matrix of data with, say, p columns.

center

mean vector of the distribution or second data vector of length p

cov

covariance matrix (p x p) of the distribution

weight

the weight of the parameters

Value

weighted Mahalanobis distance will be returned

Details

the weight of parameters is defined by users;if you do not define the weight,the corresponding percent contributions of the parameters based on the principal component analysis scheme will be used instead

References

passage: "APPLICATION OF WEIGHTED MAHALANOBIS DISTANCE DISCRIMINANT ANALYSIS METHOD TO CLASSIFICATION OF ROCK MASS QUALITY",whose author is YAO Yinpei

Examples

##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.
x=iris[1:50,1:4]
center=colMeans(x)
cov=var(x)
weight=diag(rep(0.25,4))
wmahalanobis(x,center,cov,weight)

## The function is currently defined as
function (x, center, cov, weight) 
{
    if (is.vector(x)) 
        x = matrix(x, ncol = length(x))
    else x=as.matrix(x)
    x <- sweep(x, 2, center)
    cov <- weight %*% solve(cov)
    retval <- diag(x %*% cov %*% t(x))
    retval
  }