Multivariate Normal Variance Mixtures in R: The R Package nvmix

Multivariate Normal Variance Mixtures in R: The R Package nvmix

multivariate normal variance mixtures, Student t, Gauss, distribution function,
density, random number generation

We present the features and implementation of the R package nvmix for the class of
normal variance mixtures including Student t and normal distributions. The package provides functionalities for such distributions, notably the evaluation of the distribution and
density function as well as likelihood-based parameter estimation. The distributional family is specified through the quantile function of the underlying mixing random variable.
The R package nvmix thus allows one to model multivariate distributions well beyond
the classical multivariate normal and t case. Additional functionalities include graphical
goodness-of-fit assessment, the estimation of the risk measures value-at-risk and expected
shortfall for univariate normal variance mixture distributions and functions to work with
normal variance mixture copulas, such as sampling and the evaluation of normal variance
mixture copulas and their densities. Furthermore, the package nvmix also provides functionalities for the evaluation of the distribution and density function as well as random
variate generation for the more general class of grouped normal variance mixtures.

Erik Hintz

https://www.jstatsoft.org/article/view/v102i02

University of Waterloo

April 2022

Fajar bagus W

PDF

English

Text