MGLM: Multivariate Response Generalized Linear Models

Provides functions that (1) fit multivariate discrete distributions, (2) generate random numbers from multivariate discrete distributions, and (3) run regression and penalized regression on the multivariate categorical response data. Implemented models include: multinomial logit model, Dirichlet multinomial model, generalized Dirichlet multinomial model, and negative multinomial model. Making the best of the minorization-maximization (MM) algorithm and Newton-Raphson method, we derive and implement stable and efficient algorithms to find the maximum likelihood estimates. On a multi-core machine, multi-threading is supported.

Install the latest version of this package by entering the following in R:
AuthorYiwen Zhang <> and Hua Zhou <>
Date of publication2017-03-27 15:21:50 UTC
MaintainerYiwen Zhang <>
LicenseGPL (>= 2)

View on CRAN


ddirm Man page
dgdirm Man page
dist Man page Man page
DMD.DM.reg Man page Man page
DMD.GDM.reg Man page
DMD.MN.reg Man page
DMD.NegMN.Alpha.reg Man page Man page
DMD.NegMN.reg Man page
dmn Man page
dmultn Man page
dneg Man page
dnegmn Man page
glm.private Man page
kr Man page
lsq_threshold Man page
lsq_thresholding Man page
matrix_threshold Man page
MGLM Man page
MGLMfit Man page
MGLMfit-class Man page
MGLM.loss Man page
MGLM-package Man page
MGLMreg Man page
MGLMreg-class Man page
MGLMsparsereg Man page
MGLMsparsereg-class Man page Man page
MGLMtune Man page
MGLMtune-class Man page
objfun Man page
objfun.grad Man page
objfun.hessian Man page
predict,ANY-method Man page
predict-methods Man page
predict,MGLMreg-method Man page
print,ANY-method Man page
print-methods Man page
print,MGLMfit-method Man page
print,MGLMreg-method Man page
print,MGLMsparsereg-method Man page
print, MGLMtune-method Man page
print,MGLMtune-method Man page
rdirm Man page
rgdirm Man page
rmn Man page
rnaseq Man page
rnegmn Man page
svt Man page

Questions? Problems? Suggestions? or email at

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.