fit.mix.miss.init

split_data

Optional list of initial mean vectors.

init_means

Optional list of initial covariance matrices.

init_covs

Optional vector of initial cluster proportions.

init_props

Parameter Initialization for Mixture of Multivariate Normals.

Parameter estimation and classification for Gaussian Mixture Models (GMMs) in the presence of missing data. This package uses an expectation conditional maximization algorithm to obtain maximum likelihood estimates for all model parameters and maximum a posteriori classifications of the input vectors. For additional details, please see McCaw ZR, Julienne H, Aschard H. "MGMM: an R package for fitting Gaussian Mixture Models on Incomplete Data." <doi:10.1101/2019.12.20.884551>.

fit.mix.miss.init: Parameter Initialization for Mixture of Multivariate Normals.

Description

Usage

Arguments