gamlss.mx: Fitting Mixture Distributions with Generalized Additive Models for Location Scale and Shape

CRAN package: https://CRAN.R-project.org/package=gamlss.mx
GitHub repository: https://github.com/gamlss-dev/gamlss.mx/
Project website: https://www.gamlss.com/

Overview

The package provides facilities for fitting a mixture distributions within the GAMLSS framework, (Generalized Additive Models for Location Scale and Shape), see: Stasinopoulos, Rigby, Heller, Voudouris, De Bastiani (2017, Chapter 7). Finite Mixture Distributions.) Any finite mixture distribution can be fitted from the selection of distributions provided by the package gamlss.dist. Fitting a finite mixture for the response is appropriate when the user is suspecting that the distribution of the response is bimodal or that it can be approximated better using a finite mixture. The functions of the package are;

• gamlssMX(): this function mixed, possible K, distributions with no parameters in common see age 197 of Stasinopoulos at al. (2017)) The function has methods print(), fitted(), coef(),formula(), model.matrix(), predict(), resid(), and update().

• gamlssNP(): this function mixed, possible K, distributions with parameters in common see age 207 of Stasinopoulos at al. (2017)). The function has methods print(), fitted(), coef(),family(), resid(), and plot().

• gamlssMXfits(): This functions fits several gamlssMX() ans repoets the one with best deviance.

• dMX() and pMX(): functions to get the pdf and cdf, respectively, of a finite mixture distribution.

• get_pdfMX(), get_cdfMX(), get_qfunMX(): getting the pdf, cdf and inverse cdf (q function), functions respsectively, from a fitted gamlssMX object for a specified observation. The saved object is a function.

• plotMP():

To visit the manual pages please type;

help(package = "gamlss.mx")

Installation

The development version of gamlss.mx packagecan be installed via

install.packages("gamlss.mx",
  repos = c("https://gamlss-dev.R-universe.dev",
            "https://cloud.R-project.org"))

Licence

The package is available under the General Public License version 3 or version 2