pcaRobust: Robust Principal Components Analysis...

In abnormally-distributed/cvreg: Cross Validation and Robust Estimation Utilities

Description

This applies the outlier detection method of Filzmoser, Maronna, and Werner (2008) to obtain weights, which are used to construct a weighted covariance matrix which is in turn used for principal components analysis.

Usage

pcaRobust(
  x,
  ncomp = min(nrow(x) - 1, ncol(x)),
  scale = TRUE,
  control = list(explvar = 0.96, crit.M1 = 0.33, crit.c1 = 2.5, crit.M2 = 0.25, crit.c2
    = 0.975, cs = 0.25, outbound = 0.25)
)

Arguments

x	a matrix or data frame containing only numeric variables
ncomp	the number of components to retain.
scale	should the variables be scaled prior to analysis? Defaults to TRUE.
control	a list of control options for the outlier identification step. usually these will not need to be changed.

Value

an object of class PrincipalComp

References

Filzmoser, P., Maronna, M., & Werner., M. (2008) Outlier identification in high dimensions, Computational Statistics and Data Analysis, 52, 1694-1711.

abnormally-distributed/cvreg documentation built on May 3, 2020, 3:45 p.m.