The score(), information(),
dmodel(), and pmodel() auxiliary functions for
glm objects can now be evaluated at a supplied response
under the fitted model design.
The score() and information() auxiliary
functions for betareg objects can now be evaluated at a
supplied response under the fitted model design.
Added dmodel(), pmodel(), and
qmodel() auxiliary functions for betareg
objects fitted with dist = "beta". These evaluate beta
densities, distribution functions, and quantile functions under the
fitted model design.
Added Pmat() and Qmat() auxiliary
functions for betareg objects fitted with
dist = "beta". These return the P_t and
Q_t matrices used in bias calculations.
betareg objects fitted with dist = "xbeta"
or dist = "xbetax". Such objects are now rejected with an
informative error.Standardized the interfaces of the dmodel(),
pmodel(), and qmodel() auxiliary functions for
glm objects around the fitted model design, in line with
score() and information(). Consequently,
dmodel() and pmodel() now accept a response
rather than a data frame, and qmodel() evaluates one
probability per fitted observation. This replaces the previous interface
for evaluation at arbitrary data frames.
Added new tests for existing and new functionality.
Various documentation updates.
Pmat() and Qmat() to the auxiliary
functions for enriched glm objects. These return the
P_t and Q_t matrices used in mean and median
bias-reduction calculations, and can be evaluated at user-supplied
regression and dispersion parameter values.Added new tests for existing and new functionality.
Various documentation updates.
Updated package metadata, including adding brglm2 to
Suggests.
Deprecated enriched_glm() as it might lead to
scoping issues. Users are recommended to use the call
enrich(glm(...)) or
glm(...) |> enrich().
Fixed documentation links, and other minor documentation improvements
dmu.deta -> d2mu.deta)
for betareg enrichment, which would cause failures with
get_bias_function() and other methods.SuppDists.wedderburn family from the
gnm R package.betareg objects.glm
and betareg objects.get_information_function for betareg
objects returns a function that can compute observed information
matrices (by setting type = "observed").get_information_function now returns a function that
can compute the Cholesky decomposition of the information matrix (by
setting CHOL = TRUE).simulate methods (coming form
get_simulate_function) now check for correct length of
coefficient vector if this is specified.enrich.family can return 4th derivatives of the a
function and other characteristics of the exponential family.enrich method for betareg objects
(enrichment options with scores, information, bias and simulate).enrich.family including a
description of the exponential family.with
argument of enrich methods.bias
function was passed a named vectors.get_dmodel_function,
get_pmodel_function, get_qmodel_functionenriched_glm can now be used to fit GLMs and get
objects that are enriched with auxiliary functions and other components
when compared to their glm counterparts.?enrich.family.get_dmodel_function.glm,
get_pmodel_function.glm,
get_qmodel_function.glm.lm objects.contributions = TRUE for getting score contributions.glm objects.glm objects.glm objects.glm objects.