rrcov (version 0.4-01)

Cov: Classical Estimates of Multivariate Location and Scatter

Description

Computes the classical estimates of multivariate location and scatter. Returns an S4 class Cov with the estimated center, cov, Mahalanobis distances and weights based on these distances. The class Cov is used as a base class for the classes representing the different robust estimators.

Usage

Cov(x, unbiased=TRUE)

Arguments

x

a matrix or data frame. As usual, rows are observations and columns are variables.

unbiased

whether to return the unbiased estimate of the covariance matrix. Default is unbiased = TRUE

Value

• An object of class "Cov".

concept

High breakdown point

See Also

Cov-class

Examples

data(hbk)
hbk.x <- data.matrix(hbk[, 1:3])
cv <- Cov(hbk.x)
cv
summary(cv)
plot(cv)