VGAMextra (version 0.0-6)
Additions and Extensions of the 'VGAM' Package
Description
Extending the functionalities of the 'VGAM' package with
additional functions and datasets. At present, 'VGAMextra'
comprises new family functions (ffs) to estimate several time
series models by maximum likelihood using Fisher scoring,
unlike popular packages in CRAN relying on optim(), including
ARMA-GARCH-like models, the Order-(p, d, q) ARIMAX model (non-
seasonal), the Order-(p) VAR model, error correction models
for cointegrated time series, and ARMA-structures with Student-t
errors. For independent data, new ffs to estimate the inverse-
Weibull, the inverse-gamma, the generalized beta of the second
kind and the general multivariate normal distributions are
available. In addition, 'VGAMextra' incorporates new VGLM-links
for the mean-function, and the quantile-function (as an alternative
to ordinary quantile modelling) of several 1-parameter distributions,
that are compatible with the class of VGLM/VGAM family functions.
Currently, only fixed-effects models are implemented. All functions
are subject to change; see the NEWS for further details on the
latest changes.