cluster.fmmstil.K.parallel.random: Clustering using mstil given a fixed number of clusters in...

In henrylobster/mstil: 'Multivariate Skew t Distribution with Independent Logistic Skewing Function (MSTIL)'

Description

Clustering using mstil given a fixed number of clusters in parallel using random initial parameters.

Usage

cluster.fmmstil.K.parallel.random(
  x,
  K,
  ncore = 1,
  numTrial = 1,
  criteria = c("ICL", "BIC", "AIC"),
  init.cluster.method,
  init.param.method,
  show.progress = TRUE,
  control = list()
)

Arguments

x	matrix of quantiles of size n x k. Each row is taken as a quantile.
K	a positive integer, represents the number of clusters in the model.
ncore	a positive integer, represents the number of cpu threads to be used in parallel. By default 1.
numTrial	a positive integer, represents the number of trials to be evaluated. By default 1.
criteria	Either 'ICL', 'BIC', or 'AIC'. Represents the type of information criteria used for model selection. By default 'ICL'.
init.cluster.method	a function of x, K that seperates x into K initial clusters.
init.param.method	a function of x, returns initial parameters.
show.progress	a logical value. If TRUE, progress of the algorithm will be printed in console. By default TRUE.
control	list of control variables, it accepts all control arguments used in fit.fmmstil.r and fit.fmmsil.

Value

a list with components:

restricted	a list containing details of the best fitted fmmstil.r.
unrestricted	a list containing details of the best fitted fmmstil.
recordR	a list of list containing details all fitted fmmstil.r.

henrylobster/mstil documentation built on Sept. 25, 2020, 3:48 p.m.