arw_adjustment: Atkinson–Riani–Welsh (ARW) Adjusted Cutoff for Robust...

In MVN: Multivariate Normality Tests

Atkinson–Riani–Welsh (ARW) Adjusted Cutoff for Robust Mahalanobis Distances

Description

Implements the ARW procedure to compute an adjusted cutoff for squared Mahalanobis distances, then re-estimates location and scatter excluding points beyond the cutoff.

Usage

arw_adjustment(x, m0, c0, alpha, pcrit)

Arguments

x	A numeric matrix or data frame of observations (rows) by variables (columns), with at least 2 columns.
m0	A numeric vector of initial location estimates (length equal to number of columns in x).
c0	A numeric covariance matrix corresponding to m0.
alpha	Numeric; significance level for the chi-square threshold. Defaults to 0.05 if not provided.
pcrit	Numeric; minimal proportion for the adjusted cutoff. If not provided, it is computed as: (0.24 - 0.003p)/\sqrt{n} if p \leq 10, or (0.252 - 0.0018p)/\sqrt{n} if p > 10.

Value

A list with the following components: m, the updated location vector after excluding outliers; c, the updated covariance matrix; cn, the adjusted cutoff on Mahalanobis distances; w, a logical vector indicating which observations have distance less than or equal to cn.

MVN documentation built on June 10, 2025, 5:12 p.m.