covPC: Covariance Matrix Estimation from princomp Object

In pcaPP: Robust PCA by Projection Pursuit

Covariance Matrix Estimation from princomp Object

Description

computes the covariance matrix from a princomp object. The number of components k can be given as input.

Usage

covPC(x, k, method)

Arguments

x	an object of class princomp.
k	number of PCs to use for covariance estimation (optional).
method	method how the PCs have been estimated (optional).

Details

There are several possibilities to estimate the principal components (PCs) from an input data matrix, including the functions PCAproj and PCAgrid. This function uses the estimated PCs to reconstruct the covariance matrix. Not all PCs have to be used, the number k of PCs (first k PCs) can be given as input to the function.

Value

cov	the estimated covariance matrix
center	the center of the data, as provided from the princomp object.
method	a string describing the method that was used to calculate the PCs.

Author(s)

Heinrich Fritz, Peter Filzmoser <[e-mail]>

References

C. Croux, P. Filzmoser, M. Oliveira, (2007). Algorithms for Projection-Pursuit Robust Principal Component Analysis, Chemometrics and Intelligent Laboratory Systems, Vol. 87, pp. 218-225.

See Also

PCAgrid, PCAproj, princomp

Examples

  # multivariate data with outliers
  library(mvtnorm)
  x <- rbind(rmvnorm(200, rep(0, 6), diag(c(5, rep(1,5)))),
             rmvnorm( 15, c(0, rep(20, 5)), diag(rep(1, 6))))
  pc <- princomp(x)
  covPC(pc, k=2)

pcaPP documentation built on Oct. 24, 2022, 9:07 a.m.