NEW FEATURE
- New function
pdf()
to compute the conditional log-likelihood.
BUG FIX
- add compiler flag to prevent boost/functional from using
unary_function
.
BUG FIX
- fix unnecessary error when calling
vinereg()
with weights.
NEW FEATURE
- New function
cll()
to compute the conditional log-likelihood.
BUG FIX
- avoid bit-wise operations on boolean variables (fixes warnings for clang>=14).
DEPENDS
- require recent version of vinecopulib (>= 0.6.1.1.2) to ensure compatible RcppThread versions.
BUG FIXES
require()
calls with single argument in vignettes.
vinereg 0.8.0
BUG FIXES
-
fix
cpit()
(last conditioning was sometimes omitted). -
prevent
rvinecopulib
from spawning own threads.
NEW FEATURES
- add
uscale
option to allow for external marginal modeling.
BUG FIXES
- fix simulated data size in documentation examples.
BUG FIXES
- properly handle case where no covariates are selected.
- conditional use of packages in Suggests.
BUG FIXES
- remove bias in quantiles for discrete variables.
This is a maintenance release following an update in rvinecopulib.
DEPENDS
- requires rvinecopulib (>= 0.5.4.1.0) to fix an unitialized value issue.
NEW FEATURES
- variables generated from
factor
s are now named with the corresponding factor level.
DEPENDENCIES
- removed dependence on future and furrr packages.
NEW FEATURES
-
faster runtimes, especially for parallelized code.
-
handle discrete variables properly with both parametric and nonparametric pair-copulas.
REMOVED FEATURES
- removed support for
uscale
argument.
NEW FEATURES
- new function
cpit()
to compute the conditional cdf.
DEPENDS
- require rvinecopulib (>= 0.3.0) due to breaking changes in this package.
BUG FIXES
-
prevent nan errors in loglik calculation.
-
allow for empty and bivariate models.
-
properly pass degree parameter for margin al estimation.
BUG FIXES
-
Fix handling of
uscale
infitted.vinereg()
. -
Fix handling of
mult
parameter for pair-copula fits invinereg()
. -
Fix orientation of asymmetric pair-copulas.
DEPENDS
- Use
furrr
andfuture
packages instead ofparallel
,doParallel
, andforeach
for parallelization.
NEW FEATURES
-
New
print()
andsummary()
generics forvinereg
objects. -
New
plot_effects()
method to show the marginal effects of variables. -
Allow to predict the mean with
predict(object, alpha = NA)
.
- First official release.