dcsis: Calculate the distance covariance

In jofie/DistCov: Functions for distance correlations

Description

Calculate the distance covariance

Usage

dcsis(response, X, bias.corr = TRUE, metr.response = "euclidean",
  metr.X, use = "all", top = NULL, threshold = NULL,
  return.all = FALSE)

Arguments

X	contains either the first sample or its corresponding distance matrix. In the first case, this input can be either a vector of positive length, a matrix with one column or a data.frame with one column. In this case, type.X must be specified as "sample". In the second case, the input must be a distance matrix corresponding to the sample of interest. In this second case, type.X must be "distance".
bias.corr	logical; indicates if the bias corrected version of the sample distance covariance should be calculated.
metr.X	specifies the metric which should be used for X to analyse the distance covariance. TO DO: Provide details for this.
use	: "all" uses all observations, "complete.obs" only uses observations that are complete for all variables, "pairwise.complete.obs" uses pairwise complete observations for computing distance covariances

Value

numeric giving the distance covariance between samples X and Y.

jofie/DistCov documentation built on May 23, 2019, 9:02 p.m.