mahalanobis_dist: Calculate Mahalanobis distances (tolerant to non positive...

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

Description

the difference between this and the base function mahalanobis is that this can tolerate a non positive-semidefinite covariance matrix.

Usage

mahalanobis_dist(
  x,
  center = colMeans,
  cov = function(x) crossprod(x)/nrow(x),
  inverted = FALSE,
  tol = 1e-12
)

Arguments

x	a matrix of numeric data
center	defaults to column medians but a vector of means or other location measures can be supplied.
cov	either a covariance matrix or a function to calculate one. defaults to an adaptive huber method.
inverted	defaults to FALSE. change to true if you are providing a precision matrix.
tol	tolerance

Value

a vector

Examples

mahalanobis_dist(x)

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