FitMix: Fit Multivariate Mixture Distribution

In zrmacc/MNMix: Missingness Aware Gaussian Mixture Models

Fit Multivariate Mixture Distribution

Description

Given a matrix of random vectors, estimates the parameters for a mixture of multivariate normal distributions. Accommodates arbitrary patterns of missingness, provided the elements are missing at random (MAR).

Usage

FitMix(
  data,
  k = 2,
  init_means = NULL,
  fix_means = FALSE,
  init_covs = NULL,
  lambda = 0,
  init_props = NULL,
  maxit = 100,
  eps = 1e-06,
  report = FALSE
)

Arguments

data	Numeric data matrix.
k	Number of mixture components. Defaults to 2.
init_means	Optional list of initial mean vectors.
fix_means	Fix means to their starting values? Must initialize.
init_covs	Optional list of initial covariance matrices.
lambda	Optional ridge term added to covariance matrix to ensure positive definiteness.
init_props	Optional vector of initial cluster proportions.
maxit	Maximum number of EM iterations.
eps	Minimum acceptable increment in the EM objective.
report	Report fitting progress?

Value

Object of class mix.

zrmacc/MNMix documentation built on July 3, 2024, 7:48 p.m.