Releases: bsvars/bsvars
bsvars 3.2
The package is under intensive development, and more functionality will be provided soon! To see the package ROADMAP towards the next version.
Have a question, or suggestion, or wanna get in touch? Join the package DISCUSSION forum.
- The package includes the first version of the vignette 5
- Updates on the website https://bsvars.org/bsvars/
- New plots with axes reading variable names, time scale, and letting you specify structural shock names! 97
- Improved examples for forecasting with exogenous variables. Sample matrices included in the package. Fixed the bug in cpp code for forecasting. Thanks to @DawievLill for asking for clarity! 96
bsvars 3.1
The package is under intensive development, and more functionality will be provided soon! To see the package ROADMAP towards the next version.
Have a question, or suggestion, or wanna get in touch? Join the package DISCUSSION forum.
- A NEW MODEL! An SVAR with t-distributed structural shocks facilitating identification through non-normality is now included in the package with all the necessary functionality #84
- New ways of verifying identification through heteroskedasticity or non-normality using method
verify_identification()#84 - Improve coding of
forecastcpp function and R methods #89 - Included or updated legend in FEVD and HD plots as requested by @ccoleman9 #85
bsvars 3.0.1
The package is under intensive development, and more functionality will be provided soon! To see the package ROADMAP towards the next version.
Have a question, or suggestion, or wanna get in touch? Join the package DISCUSSION forum.
- Fixed the bugs that started coming up in the new tested version of Armadillo and RcppArmadillo #82 and RcppCore/RcppArmadillo#443
- Corrected the computations of
verify_autoregression#82
bsvars 3.0
The package is under intensive development, and more functionality will be provided soon! To see the package ROADMAP towards the next version.
Have a question, or suggestion, or wanna get in touch? Join the package DISCUSSION forum.
- The package has a logo! And it's beautiful! #37
- The package includes
summarymethods #1 - The package includes
plotmethods #36 - Method
forecastallow for conditional forecasting given provided future trajectories of selected variables #76 - Sparse mixture and Markov-switching models can now have more than 20 regimes #57
- A new, more detailed, package description #62
- The website features the new logo. And includes some new information #38
- Updates on documentation to accommodate the fact that some generics and functions from package bsvars will be used in a broader family of packages, first of which is bsvarSIGNs. Includes updates on references. #63
- Fixed
compute_fitted_values(). Now it's correctly sampling from the predictive data density. #67 - Fixed some bugs that did not create problems #55
- Got rid of filling by reference in the samplers for the sake of granting the exported cpp functions usability #56
- Coded
compute_*()functions as generics and methods #70 - Updated code for forecast error variance decompositions for heteroskedastic models (qas prompted by @adamwang15) #69
bsvars v2.1.0
The new version 2.1.0 of the bsvars package for Bayesian Estimation of Structural Vector Autoregressive Models in R is now available on CRAN!
The official CRAN page is: https://cran.r-project.org/package=bsvars
Package description
The package provides efficient algorithms for Bayesian estimation of Structural Vector Autoregressive (SVAR) models via Markov chain Monte Carlo methods. A wide range of SVAR models is considered, including homo- and heteroskedastic specifications and those with non-normal structural shocks. All models include three-level equation-specific local-global hierarchical prior distribution for the estimated level of shrinkage for autoregressive and structural parameters.
The new version 2.1.0
This version is backward compatible with v2.0.0
New Features!
- The possibility of specifying exogenous variables that might include any measurements but not lags of the dependent variable, as in a VARX model or deterministic terms including a t 8000 rend, quadratic trend, seasonal and other dummies.
- A website scrutinising the package's main features available at bsvars.github.io/bsvars/.
- Verification of hypothesis of homoskedasticity using
verify_volatility()method. - Verification of hypotheses on autoregressive parameters using
verify_autoregressive()method. - Sample data update for the reproduction of Lütkepohl, Shang, Uzeda, Woźniak (2023), including exogenous variables. Upload dependent variables using
data(us_fiscal_lsuw)and the exogenous variables usingdata(us_fiscal_ex). - Fixed compilation buggs.
Further developments
The package is under intensive development, and more functionalities will be provided soon! To see the package ROADMAP towards the next version 2.2.0.
Join the conversation!
Have a question, or suggestion, or wanna get in touch? Join the package DISCUSSION forum.
Greetings, Tomasz @donotdespair
Contributors
Assets 2
bsvars v2.0.0
The new version 2.0.0 of the bsvars package for Bayesian Estimation of Structural Vector Autoregressive Models in R is now available on CRAN!
The official CRAN page is: https://cran.r-project.org/package=bsvars
Package description
The package provides efficient algorithms for Bayesian estimation of Structural Vector Autoregressive (SVAR) models via Markov chain Monte Carlo methods. A wide range of SVAR models is considered, including homo- and heteroskedastic specifications and those with non-normal structural shocks. All models include three-level equation-specific local-global hierarchical prior distribution for the estimated level of shrinkage for autoregressive and structural parameters.
The new version 2.0.0
This version is not backward compatible, so you might need to rewrite your existing scripts. This is because the new version:
- includes a new
estimatemethod replacing the estimation functions for individual modelsestimate_bsvar_*(). To estimate the model just use theestimateroutine:
library(bsvars) # upload the package
data(us_fiscal_lsuw) # load the data
specification = specify_bsvar_sv$new(us_fiscal_lsuw, p = 2) # specify the model and set seed
posterior = estimate(specification, 10000) # estimate the model THAT'S IT!
- it also facilitates the use of the
|>pipe for simplified workflows. The script above can be rewritten as:
library(bsvars) # upload the package
data(us_fiscal_lsuw) # load the data
us_fiscal_lsuw |>
specify_bsvar_sv$new(p = 2) |> # specify the model
estimate(S = 10000) _> posterior # estimate the model VOILA!
- provides routines for fast computations for impulse responses, forecast error variance decompositions, historical decompositions, computations of structural shocks, fitted values, conditional standard deviations, and regime probabilities for MS and MIX models,
- implements a new three-level equation-specific local-global hierarchical prior distribution for the estimated level of shrinkage for autoregressive and structural parameters,
- includes a new model similar to that by Chan, Koop, Yu (2022)
- implements even faster random number generators to speed things up even more!
- and many more that can be found at NEWS
Further developments
The package is under intensive development, and more functionalities will be provided soon! To see the package ROADMAP towards the next version 2.1.0.
Join the conversation!
Have a question, or suggestion, or wanna get in touch? Join the package DISCUSSION forum.
Greetings, Tomasz @donotdespair
Contributors
Assets 3
bsvars 1.0.0
The bsvars package for Bayesian Estimation of Structural Vector Autoregressive Models in R is now available on CRAN!
The official CRAN page is: https://cran.r-project.org/package=bsvars
The package provides efficient algorithms for Bayesian estimation of Structural Vector Autoregressive (SVAR) models via Markov chain Monte Carlo methods. A wide range of SVAR models is considered, including homo- and heteroskedastic specifications and those with non-normal structural shocks.
The package is under intensive development and more functionality will be provided soon!