Learn R Programming

poisson.glm.mix (version 1.4)

Fit High Dimensional Mixtures of Poisson GLMs

Description

Mixtures of Poisson Generalized Linear Models for high dimensional count data clustering. The (multivariate) responses can be partitioned into set of blocks. Three different parameterizations of the linear predictor are considered. The models are estimated according to the EM algorithm with an efficient initialization scheme .

Copy Link

Version

Install

install.packages('poisson.glm.mix')

Monthly Downloads

301

Version

1.4

License

GPL-2

Maintainer

Panagiotis Papastamoulis

Last Published

August 19th, 2023

Functions in poisson.glm.mix (1.4)

bkmodel

EM algorithm for the \(\beta_{k}\) (m=3) Poisson GLM mixture.
pois.glm.mix

Main call function of the package.
mylogLikePoisMix

Function to compute the loglikelihood of the mixture.
init1.1.jk.j

1st step of Initialization 1 for the \(\beta_{jk}\) (\(m=1\)) or \(\beta_{j}\) (\(m=2\)) parameterization.
init2.jk.j

Initialization 2 for the \(\beta_{jk}\) (\(m=1\)) or \(\beta_{j}\) (\(m=2\)) parameterization.
init2.k

Initialization 2 for the \(\beta_k\) parameterization (\(m=3\)).
poisson.glm.mix

Estimation of high dimensional Poisson GLMs via EM algorithm.
sim.data

Simulated data set of 500 observations
init1.2.jk.j

2nd step of Initialization 1 for the \(\beta_{jk}\) (\(m=1\)) or \(\beta_{j}\) (\(m=2\)) parameterization.
bjmodel

EM algorithm for the \(\beta_{j}\) (m=2) Poisson GLM mixture.
init1.k

Initialization 1 for the \(\beta_{k}\) parameterization (\(m=3\)).
bjkmodel

EM algorithm for the \(\beta_{jk}\) (m=1) Poisson GLM mixture.