Returns a full NxN matrix of Mahalanobis distances among rows of X, using a shrunken inverse covariance.
No block-based exclusion is performed.
Usage
# S3 method for class 'mahalanobis'
pairwise_dist(obj, X)
Arguments
- obj
A distance function object of class c("mahalanobis", "distfun").
- X
A numeric matrix (rows = observations, columns = variables).
Value
An N x N numeric matrix of pairwise Mahalanobis distances.
Details
Uses corpcor::invcov.shrink on X to estimate the inverse covariance matrix
and then computes mahalanobis(...) for each row vs. each other row.
Examples
X <- matrix(rnorm(100), 10, 10)
dist_obj <- mahadist()
dist_matrix <- pairwise_dist(dist_obj, X)
#> Error in UseMethod("pairwise_dist"): no applicable method for 'pairwise_dist' applied to an object of class "c('mahalanobis', 'distfun')"