Package index • bvhar

Package

The bvhar package

bvhar bvhar-package: bvhar: Bayesian Vector Heterogeneous Autoregressive Modeling

Frequentist modeling

Vector autoregressive (VAR) and heterogeneous autoregressive (VHAR) models.

var_lm() print(<varlse>) logLik(<varlse>) AIC(<varlse>) BIC(<varlse>) is.varlse() is.bvharmod() knit_print(<varlse>): Fitting Vector Autoregressive Model of Order p Model

vhar_lm() print(<vharlse>) logLik(<vharlse>) AIC(<vharlse>) BIC(<vharlse>) is.vharlse() knit_print(<vharlse>): Fitting Vector Heterogeneous Autoregressive Model

VARtoVMA(): Convert VAR to VMA(infinite)

VHARtoVMA(): Convert VHAR to VMA(infinite)

summary(<varlse>) print(<summary.varlse>) knit_print(<summary.varlse>): Summarizing Vector Autoregressive Model

summary(<vharlse>) print(<summary.vharlse>) knit_print(<summary.vharlse>): Summarizing Vector HAR Model

Prior specification

Prior settings for Bayesian models.

set_bvar() set_bvar_flat() set_bvhar() set_weight_bvhar() print(<bvharspec>) is.bvharspec() knit_print(<bvharspec>): Hyperparameters for Bayesian Models

set_ssvs() print(<ssvsinput>) is.ssvsinput() knit_print(<ssvsinput>): Stochastic Search Variable Selection (SSVS) Hyperparameter for Coefficients Matrix and Cholesky Factor

set_lambda() set_psi() print(<bvharpriorspec>) is.bvharpriorspec() knit_print(<bvharpriorspec>): Hyperpriors for Bayesian Models

set_horseshoe() print(<horseshoespec>) is.horseshoespec() knit_print(<horseshoespec>): Horseshoe Prior Specification

set_ng() print(<ngspec>) is.ngspec() experimental: Normal-Gamma Hyperparameter for Coefficients and Contemporaneous Coefficients

set_dl() print(<dlspec>) is.dlspec() experimental: Dirichlet-Laplace Hyperparameter for Coefficients and Contemporaneous Coefficients

set_ldlt() set_sv() print(<covspec>) is.covspec() is.svspec() is.ldltspec() experimental: Covariance Matrix Prior Specification

set_intercept() print(<interceptspec>) is.interceptspec() knit_print(<interceptspec>): Prior for Constant Term

Bayesian modeling

Bayesian VAR and Bayesian VHAR models.

var_bayes() print(<bvarsv>) print(<bvarldlt>) knit_print(<bvarsv>) knit_print(<bvarldlt>) maturing: Fitting Bayesian VAR with Coefficient and Covariance Prior

bvar_minnesota() print(<bvarmn>) print(<bvarhm>) logLik(<bvarmn>) AIC(<bvarmn>) BIC(<bvarmn>) is.bvarmn() knit_print(<bvarmn>) knit_print(<bvarhm>): Fitting Bayesian VAR(p) of Minnesota Prior

bvar_flat() print(<bvarflat>) logLik(<bvarflat>) AIC(<bvarflat>) BIC(<bvarflat>) is.bvarflat() knit_print(<bvarflat>): Fitting Bayesian VAR(p) of Flat Prior

vhar_bayes() print(<bvharsv>) print(<bvharldlt>) knit_print(<bvharsv>) knit_print(<bvharldlt>) maturing: Fitting Bayesian VHAR with Coefficient and Covariance Prior

bvhar_minnesota() print(<bvharmn>) print(<bvharhm>) logLik(<bvharmn>) AIC(<bvharmn>) BIC(<bvharmn>) is.bvharmn() knit_print(<bvharmn>) knit_print(<bvharhm>): Fitting Bayesian VHAR of Minnesota Prior

summary(<normaliw>) print(<summary.normaliw>) knit_print(<summary.normaliw>): Summarizing Bayesian Multivariate Time Series Model

print(<summary.bvharsp>) knit_print(<summary.bvharsp>) summary(<ssvsmod>) summary(<hsmod>) summary(<ngmod>): Summarizing BVAR and BVHAR with Shrinkage Priors

Forecasting

predict(<varlse>) predict(<vharlse>) predict(<bvarmn>) predict(<bvharmn>) predict(<bvarflat>) predict(<bvarldlt>) predict(<bvharldlt>) predict(<bvarsv>) predict(<bvharsv>) print(<predbvhar>) is.predbvhar() knit_print(<predbvhar>): Forecasting Multivariate Time Series

divide_ts(): Split a Time Series Dataset into Train-Test Set

forecast_roll() print(<bvharcv>) is.bvharcv() knit_print(<bvharcv>): Out-of-sample Forecasting based on Rolling Window

forecast_expand(): Out-of-sample Forecasting based on Expanding Window

Structural analysis

print(<bvharirf>) irf() is.bvharirf() knit_print(<bvharirf>): Impulse Response Analysis

spillover() print(<bvharspillover>) knit_print(<bvharspillover>): h-step ahead Normalized Spillover

dynamic_spillover() print(<bvhardynsp>) knit_print(<bvhardynsp>): Dynamic Spillover

Evaluation

mse(): Evaluate the Model Based on MSE (Mean Square Error)

mae(): Evaluate the Model Based on MAE (Mean Absolute Error)

mape(): Evaluate the Model Based on MAPE (Mean Absolute Percentage Error)

mase(): Evaluate the Model Based on MASE (Mean Absolute Scaled Error)

mrae(): Evaluate the Model Based on MRAE (Mean Relative Absolute Error)

relmae(): Evaluate the Model Based on RelMAE (Relative MAE)

rmsfe(): Evaluate the Model Based on RMSFE

rmafe(): Evaluate the Model Based on RMAFE

rmape(): Evaluate the Model Based on RMAPE (Relative MAPE)

rmase(): Evaluate the Model Based on RMASE (Relative MASE)

conf_fdr(): Evaluate the Sparsity Estimation Based on FDR

conf_fnr(): Evaluate the Sparsity Estimation Based on FNR

conf_fscore(): Evaluate the Sparsity Estimation Based on F1 Score

conf_prec(): Evaluate the Sparsity Estimation Based on Precision

conf_recall(): Evaluate the Sparsity Estimation Based on Recall

confusion(): Evaluate the Sparsity Estimation Based on Confusion Matrix

fromse(): Evaluate the Estimation Based on Frobenius Norm

spne(): Evaluate the Estimation Based on Spectral Norm Error

relspne(): Evaluate the Estimation Based on Relative Spectral Norm Error

Tuning

compute_logml(): Extracting Log of Marginal Likelihood

choose_bvar() choose_bvhar() print(<bvharemp>) is.bvharemp() knit_print(<bvharemp>): Finding the Set of Hyperparameters of Individual Bayesian Model

bound_bvhar() print(<boundbvharemp>) is.boundbvharemp() knit_print(<boundbvharemp>) experimental: Setting Empirical Bayes Optimization Bounds

choose_bayes() experimental: Finding the Set of Hyperparameters of Bayesian Model

Information criteria

FPE(): Final Prediction Error Criterion

HQ(): Hannan-Quinn Criterion

choose_var(): Choose the Best VAR based on Information Criteria

compute_dic(): Deviance Information Criterion of Multivariate Time Series Model

Plots

autoplot(<normaliw>): Residual Plot for Minnesota Prior VAR Model

autoplot(<summary.normaliw>): Density Plot for Minnesota Prior VAR Model

autoplot(<predbvhar>) autolayer(<predbvhar>): Plot Forecast Result

geom_eval(): Adding Test Data Layer

gg_loss(): Compare Lists of Models

autoplot(<bvharirf>): Plot Impulse Responses

autoplot(<bvharsp>): Plot the Result of BVAR and BVHAR MCMC

autoplot(<summary.bvharsp>): Plot the Heatmap of SSVS Coefficients

autoplot(<bvhardynsp>): Dynamic Spillover Indices Plot

Simulation and Random Generation

sim_var(): Generate Multivariate Time Series Process Following VAR(p)

sim_vhar(): Generate Multivariate Time Series Process Following VAR(p)

sim_mncoef(): Generate Minnesota BVAR Parameters

sim_mnvhar_coef(): Generate Minnesota BVAR Parameters

sim_mnormal(): Generate Multivariate Normal Random Vector

sim_matgaussian(): Generate Matrix Normal Random Matrix

sim_iw(): Generate Inverse-Wishart Random Matrix

sim_mniw(): Generate Normal-IW Random Family

sim_mvt(): Generate Multivariate t Random Vector

sim_gig(): Generate Generalized Inverse Gaussian Distribution

Data

etf_vix: CBOE ETF Volatility Index Dataset

Other generic functions

stableroot(): Roots of characteristic polynomial

is.stable(): Stability of the process

coef(<varlse>) coef(<vharlse>) coef(<bvarmn>) coef(<bvarflat>) coef(<bvharmn>) coef(<bvharsp>) coef(<summary.bvharsp>): Coefficient Matrix of Multivariate Time Series Models

residuals(<varlse>) residuals(<vharlse>) residuals(<bvarmn>) residuals(<bvarflat>) residuals(<bvharmn>): Residual Matrix from Multivariate Time Series Models

fitted(<varlse>) fitted(<vharlse>) fitted(<bvarmn>) fitted(<bvarflat>) fitted(<bvharmn>): Fitted Matrix from Multivariate Time Series Models