Function reference • bsvars

bsvars: Bayesian Estimation of Structural Vector Autoregressive Models

Browse package information

bsvars-package bsvars: Bayesian Estimation of Structural Vector Autoregressive Models

Data

Upload sample data set

us_fiscal_lsuw: A 3-variable US fiscal system for the period 1948 Q1 -- 2023 Q2

us_fiscal_ex: A 3-variable system of exogenous variables for the US fiscal model for the period 1948 Q1 -- 2023 Q2

Model specification

Choose a model to work with

specify_bsvar: R6 Class representing the specification of the homoskedastic BSVAR model

specify_bsvar_mix: R6 Class representing the specification of the BSVAR model with a zero-mean mixture of normals model for structural shocks.

specify_bsvar_msh: R6 Class representing the specification of the BSVAR model with Markov Switching Heteroskedasticity.

specify_bsvar_sv: R6 Class representing the specification of the BSVAR model with Stochastic Volatility heteroskedasticity.

More detailed model specification

Adjust or inspect the specified model

specify_data_matrices: R6 Class Representing DataMatricesBSVAR

specify_identification_bsvars: R6 Class Representing IdentificationBSVARs

specify_prior_bsvar: R6 Class Representing PriorBSVAR

specify_prior_bsvar_mix: R6 Class Representing PriorBSVARMIX

specify_prior_bsvar_msh: R6 Class Representing PriorBSVARMSH

specify_prior_bsvar_sv: R6 Class Representing PriorBSVARSV

specify_starting_values_bsvar: R6 Class Representing StartingValuesBSVAR

specify_starting_values_bsvar_mix: R6 Class Representing StartingValuesBSVARMIX

specify_starting_values_bsvar_msh: R6 Class Representing StartingValuesBSVARMSH

specify_starting_values_bsvar_sv: R6 Class Representing StartingValuesBSVARSV

Estimation

Run Bayesian estimation of your model and inspect the outputs

estimate(<BSVAR>): Bayesian estimation of a homoskedastic Structural Vector Autoregression via Gibbs sampler

estimate(<BSVARMIX>): Bayesian estimation of a Structural Vector Autoregression with shocks following a finite mixture of normal components via Gibbs sampler

estimate(<BSVARMSH>): Bayesian estimation of a Structural Vector Autoregression with Markov-switching heteroskedasticity via Gibbs sampler

estimate(<BSVARSV>): Bayesian estimation of a Structural Vector Autoregression with Stochastic Volatility heteroskedasticity via Gibbs sampler

estimate(<PosteriorBSVAR>): Bayesian estimation of a homoskedastic Structural Vector Autoregression via Gibbs sampler

estimate(<PosteriorBSVARMIX>): Bayesian estimation of a Structural Vector Autoregression with shocks following a finite mixture of normal components via Gibbs sampler

estimate(<PosteriorBSVARMSH>): Bayesian estimation of a Structural Vector Autoregression with Markov-switching heteroskedasticity via Gibbs sampler

estimate(<PosteriorBSVARSV>): Bayesian estimation of a Structural Vector Autoregression with Stochastic Volatility heteroskedasticity via Gibbs sampler

estimate(): Bayesian estimation of Structural Vector Autoregressions via Gibbs sampler

normalise_posterior(): Waggoner & Zha (2003) row signs normalisation of the posterior draws for matrix \(B\)

specify_posterior_bsvar: R6 Class Representing PosteriorBSVAR

specify_posterior_bsvar_mix: R6 Class Representing PosteriorBSVARMIX

specify_posterior_bsvar_msh: R6 Class Representing PosteriorBSVARMSH

specify_posterior_bsvar_sv: R6 Class Representing PosteriorBSVARSV

Forecasting

Predict future values of your variables

forecast(<PosteriorBSVAR>): Forecasting using Structural Vector Autoregression

forecast(<PosteriorBSVARMIX>): Forecasting using Structural Vector Autoregression

forecast(<PosteriorBSVARMSH>): Forecasting using Structural Vector Autoregression

forecast(<PosteriorBSVARSV>): Forecasting using Structural Vector Autoregression

forecast(): Forecasting using Structural Vector Autoregression

Structural analyses

Compute interpretable outcomes

compute_conditional_sd(): Computes posterior draws of structural shock conditional standard deviations

compute_fitted_values(): Computes posterior draws of dependent variables' fitted values

compute_historical_decompositions(): Computes posterior draws of historical decompositions

compute_impulse_responses(): Computes posterior draws of impulse responses

compute_regime_probabilities(): Computes posterior draws of regime probabilities

compute_structural_shocks(): Computes posterior draws of structural shocks

compute_variance_decompositions(): Computes posterior draws of the forecast error variance decomposition

Model diagnostics

Verify heteroskedasticity and autoregressive parameters (in preparation: structural identification)

verify_autoregression(<PosteriorBSVAR>): Verifies hypotheses involving autoregressive parameters

verify_autoregression(<PosteriorBSVARMIX>): Verifies hypotheses involving autoregressive parameters

verify_autoregression(<PosteriorBSVARMSH>): Verifies hypotheses involving autoregressive parameters

verify_autoregression(<PosteriorBSVARSV>): Verifies hypotheses involving autoregressive parameters

verify_autoregression(): Verifies hypotheses involving autoregressive parameters

verify_volatility(<PosteriorBSVAR>): Verifies heteroskedasticity of structural shocks equation by equation

verify_volatility(<PosteriorBSVARMIX>): Verifies heteroskedasticity of structural shocks equation by equation

verify_volatility(<PosteriorBSVARMSH>): Verifies heteroskedasticity of structural shocks equation by equation

verify_volatility(<PosteriorBSVARSV>): Verifies heteroskedasticity of structural shocks equation by equation

verify_volatility(): Verifies heteroskedasticity of structural shocks equation by equation