mpcmp: Mean-parametrized Conway-Maxwell Poisson Regression

mpcmp

The mpcmp package provides a collection of functions for estimation, testing and diagnostic checking for the mean-parametrized Conway-Maxwell Poisson (COM-Poisson) regression model for under- and over-dispersed count data of Huang (2017).

From version 0.3.0, mpcmp supports log-linear mean models, also allows one to incorporate regression being linked to the dispersion parameter.

Work is progressing to include a zero-inflated Conway-Maxwell-Poisson model.

Installation

Stable release on CRAN

The mpcmp package has been on CRAN since March 2019. You can install it from CRAN in the usual way:

install.packages("mpcmp")
library("mpcmp")

Development version on Github

You can use the devtools package to install the development version of mpcmp from GitHub:

# install.packages("devtools")
devtools::install_github("thomas-fung/mpcmp")
library(mpcmp)

Usage

A reference manual and some examples are available at thomas-fung.github.io/mpcmp

Citation

If you use this package to analyse your data, please use the following citation:

• Fung, T., Alwan, A., Wishart, J. and Huang, A. (2022). mpcmp: Mean-parametrized Conway-Maxwell Poisson Regression. R package version 0.3.8.

From R you can use:

citation("mpcmp")
toBibtex(citation("mpcmp"))