matdep: Function to compute the multivariate dependency matrix

In JINJINT/aLDG: Compute and evaluate the bivariate dependence

Function to compute the multivariate dependency matrix

Description

Function to compute the multivariate dependency matrix

Usage

matdep(
  data,
  methods = NULL,
  all = FALSE,
  thred = -Inf,
  wd = 1,
  trial = 0,
  ncores = NULL,
  norm = FALSE,
  abs = FALSE,
  info = "",
  dir = "./dat/"
)

Arguments

data:	feature by sample matrix
methods:	a vector of strings, could be subset of c('pearson','kendall','taustar','dcor','hsic','hoeffd','ssd')
all:	logical value, if true then compute for all methods in c('pearson','kendall','taustar','dcor','hsic','hoeffd','ssd')
thred:	only the data > thred will be used
wd:	the coefficient before the bandwidth h = wd*h_n
qd:	the quantile window to compute the adaptive bandwidth h_x = sd(x(qd))
info:	integer denote the trial number
ncores:	number of cores to use
norm:	whether scale the value to [0,1]
abs:	whether take absolute value of the value
extrainfo:	some setting related information

Value

a list of matrix

Examples

# Load example data
ans = matdep(runif(100,5,20), methods='ssd')

JINJINT/aLDG documentation built on April 1, 2022, 6:23 p.m.