gcap.extractComponents: Decompose distribution into components

In ShixiangWang/gcaputils: Utils for Package 'gcap'

Decompose distribution into components

Description

Decompose distribution into components

Usage

gcap.extractComponents(
  dat,
  dist = "norm",
  seed = 2021L,
  model_selection = "BIC",
  threshold = 0.4,
  min_prior = 0.001,
  niter = 1000,
  nrep = 5,
  min_comp = 1,
  max_comp = 10
)

Arguments

dat	a distribution represented as a numeric vector to decompose.
dist	'pois' or 'norm' (default).
seed	seed number.
model_selection	model selection strategy, default is 'BIC'. Details about custom setting please refer to flexmix package.
threshold	default is 0.5. Sometimes, the result components include adjacent distributions with similar mu (two and more distribution are very close), we use this threshold to obtain a more meaningful fit with less components.
min_prior	the minimum relative size of components, default is 0.001. Details about custom setting please refer to flexmix package.
niter	the maximum number of iterations.
nrep	number of run times for each value of component, keep only the solution with maximum likelihood.
min_comp	minimal number of components to fit, default is 1.
max_comp	maximal number of components to fit, default is 10.

Examples

set.seed(2021)
x = c(rnorm(10, 0), rnorm(50, 1), rnorm(20, 4), rnorm(5, 10))
y = gcap.extractComponents(x, max_comp = 5)
y

ShixiangWang/gcaputils documentation built on Feb. 14, 2023, 5:58 a.m.