COMMultReg-package: Conway-Maxwell-Multinomial Regression

In andrewraim/COMMultReg: Conway-Maxwell Multinomial Regression

Conway-Maxwell-Multinomial Regression

Description

Conway-Maxwell-Multinomial Regression

Details

This package provides basic drawing and density functions for the Conway-Maxwell-Multinomial (CMM) distribution, as well as functions to carry out maximum likelihood estimation (MLE) for a regression model based on CMM. The MLE method was inspired by Altham and Hankin (2012). Further details can be found in Morris, Raim, and Sellers (2020).

Computationally intensive sections are carried out in C++ with the help of Rcpp and RcppArmadillo. Logic to iterate through the multinomial sample space, without pre-generating the elements, is from the function gsl_multiset_next in the GNU GSL library (Galassi et al).

Note that some of the functions in this package currently iterate through the multinomial sample space based on m trials and k categories. These functions are suitable for situations in which m+k-1 \choose m

References

Pat M. E. Altham and Robin K. S. Hankin (2012). Multivariate generalizations of the multiplicative binomial distribution: Introducing the MM package. Journal of Statistical Software 46.

Darcy Steeg Morris, Andrew M. Raim, and Kimberly F. Sellers (2020). A Conway-Maxwell-multinomial distribution for Flexible modeling of clustered categorical data. Journal of Multivariate Analysis, 179:104651. Preprint: https://arxiv.org/abs/1911.02131.

Dirk Eddelbuettel (2013) Seamless R and C++ Integration with Rcpp. Springer, New York. ISBN

Dirk Eddelbuettel, Conrad Sanderson (2014). RcppArmadillo: Accelerating R with high-performance C++ linear algebra. Computational Statistics and Data Analysis, Volume 71, March 2014, pages 1054-1063.

M. Galassi et al, GNU Scientific Library Reference Manual, 3rd Edition, ISBN 0954612078.

andrewraim/COMMultReg documentation built on April 2, 2022, 11:04 p.m.