- Add historical decompositions and RMSE/LPS, and WAIC for analysis
- Improve the algorithm to draw sign restrictions
- Shocks are now built and checked per variable
- Fix the CRAN NOTE on missing "tangle output"
- Update FRED-datasets to 2023-10 vintage
- Newer FRED-QD files include (unannounced) small naming changes
- Fix bug from last update, where automatic ARIMA-priors where sqrt'd twice
- Thanks to Michael Wolf for pointing this out, and
- many thanks to Nirai Tomass for discovering the bug
- Update FRED-MD and FRED-QD datasets to the 2023-02 vintage
- Fix bug where warnings caused an error during automatic ARIMA-based priors
- Thanks to Martin Feldkircher for pointing this out
- Add DOI in the CITATION file for a new JSS publication
- DOI will be registered after publication on CRAN
- References now use the DOI interface instead of URLs
- Update FRED-QD and FRED-MD datasets to 2021-10
- Fix minor issues with vignette (e.g. fixed dataset, references, etc)
- Add verbosity to ARIMA-based automatic prior settings
- Add hook to simplify use of shared generics with vars
- Add README file to the package with correct URLs
- Add identification via zero and sign restrictions
- Update CITATION with the forthcoming JSS reference
- Prepare for tidy outputs in BVARverse
- Fix minor bugs and typos (internal checks, documentation, and vignette)
- Add fancy vignette with background and demonstrations
- Add new features
- New FRED-MD database and updated FRED-QD (
data("fred_md")
) - Transformation helper functions (
fred_transform()
,fred_code()
) - Add Conditional forecasting (see
?bv_fcast()
) - New replacement functions for
irf()
andpredict()
(irf(x) <- irf(x)
) - Provide wrapper for parallelised execution (
par_bvar()
)
- New FRED-MD database and updated FRED-QD (
- Improve existing features
- Enhance IRF and forecast plotting
area
argument adds polygons for credible intervalst_back
allows adding realised values before forecastscol
andfill
arguments allow changing colours- transparence is applied to sequential lines / polygons
- Improved x-axis labelling
- Regex may be used for
vars
,vars_response
, andvars_impulse
- New
type
forcoef()
,fitted()
, etc, to retrieve means / quantiles - Add constructors for the prior mean
b
argument inbv_mn()
- Auto
psi
now allows for one order of integration
- Enhance IRF and forecast plotting
- Enhance speed considerably (~2-10 times faster)
- Move IRF and forecasts out of MCMC
- Capitalise upon matrix properties
- Cached and customised multivariate normal drawing
- Optimised FEVD computation
- Fix bugs
- IRF calculation is now ordered properly (please recalculate)
- coda methods are now proper methods (potential issue on Windows)
- Vectorised
scale_hess
now works properly
- Remove deprecated functions and arguments
- Work on documentation and examples
- Update citation information
- Improve upon internal structure
- Unit tests with tinytest for development (skipped on CRAN)
- Outsource additional steps to dedicated functions
- More robustness checks and add verbosity to errors
- Tested extensively on R 4.0.0 and R 3.6.3
- Fix impulse response calculation (stray transpose of coefficients)
- Thanks, Maximilian Böck for helping us track this down
- Add some verbosity to error messages
- Prepare for next major release
- Include messages about future extensions and changes of FEVDs
- Update docs on future construction of sign restrictions
- Update docs on prediction and IRFs in
bvar()
- Add FRED-MD co-author Serena Ng to data contributors
- Clarify exact ToU of the FRED-QD dataset with St. Louis Fed
- Comply with the new modified ODC-BY 1.0 for FRED-QD
- Mention and add license to LICENSE file (linked in DESCRIPTION)
- Add the copyrighted series we are allowed to use
- Mention updates and license in the data documentation
- Fix and improve documentation
- Extend methods further
- Add
summary()
methods forbvar
,bvar_irf
andbvar_fcast
- Add
as.mcmc
method to interface with coda - Support hyperparameters and coefficients in
plot.bvar()
anddensity()
- Add
companion()
method to retrieve the companion matrix - Improve
ylim
ofplot.bvar()
density plots with multiple chains - Add
logLik()
method forbvar
objects
- Add
- Fix
bv_psi()
errors for modes other than "auto" - Change
fcast
andirf
defaults ofbvar()
toNULL
- Move from MASS to mvtnorm for
dmvnorm()
(used inlogLik()
) - Be more specific in error messages
- Add coda to suggestions for convergence assessment etc.
- Add files LICENSE, CITATION and NEWS.md
- Improve examples for further test coverage
R CMD check --run-donttest
: One warning (deprecated functions)
- Prepare for minor release 0.2.0
- Provide several standard methods for objects generated with BVAR
predict()
for ex-post forecasts and updating quantilesirf()
/fevd()
for ex-post irfs, fevds and updating quantilesfitted()
,residuals()
,coef()
andvcov()
density()
as shorthand for callingdensity()
on hyperparameters
- Add
print()
methods for intermediate objects- Includes
bv_minnesota
,bv_metropolis
and method outputs
- Includes
- Rework plotting
plot.bvar()
now supports types, subsets and multiple chains- Deprecate
bv_plot_trace()
andbv_plot_density()
- Add
density()
, including a plot method - Replace by
plot.bvar()
, incl. plotting of multiple chains
- Add
- Change plotting of
bvar_fcast
andbvar_irf
- Deprecate
bv_plot_irf(x)
forplot(x$irf)
orplot(irf(x))
- Move
conf_bands
argument topredict()
/irf()
- Deprecate
- Add plot methods for
bvar_resid
andbvar_density
- Add
sign_lim
tobv_irf()
to set maximum number of sign restriction draws - Standardise prior construction further
- Align
alpha
andlambda
, improvepsi
alignment bv_mn()
may be called with a numeric vector foralpha
and/orlambda
- Align
- Improve documentation
- Document related functions in joint
- Add details on priors
- Add less concise aliases for
bv_mh()
andbv_mn()
bv_metropolis()
andbv_minnesota()
- Fix bugs related to single confidence bands at 0.5
- Save
fred_qd
with format version 2, lowering R dependency to (>= 3.3.0) - Add vars to suggests for shared methods, import is bypassed
- Try to clarify licensing terms with the Federal Reserve
- Some copyrighted series may have to be removed
- Subset the dataset to only include variables in public domain for now
- Fix addition of prior pdfs to ML
alpha
needs an sd parameterpsi
now needs proper shape and scale parameters- Add normalising constant
- Add lines to all density plots (when supplied via ellipsis)
- Add documentation on using
scale_hess
as a vector - Add two pre-constructed dummy priors
bv_soc()
andbv_sur()
- Further split up calculation of marginal likelihood
- Update DESCRIPTION with linked DOI
- Change
\dontrun{}
examples to\donttest{}
- Fix bounds in
plot_hyper()
- Update references with links via DOI
- Add and improve examples for
print
andplot
methods R CMD check --as-cran
: No errors or warnings, one note (New submission)