choose_ssvs: Choose the Hyperparameters Set of SSVS-VAR using a Default Semiautomatic Approach

Description

This function chooses $(\tau_{0i}, \tau_{1i})$ and $(\kappa_{0i}, \kappa_{1i})$ using a default semiautomatic approach.

Usage

choose_ssvs(
  y,
  ord,
  type = c("VAR", "VHAR"),
  param = c(0.1, 10),
  include_mean = TRUE,
  gamma_param = c(0.01, 0.01),
  mean_non = 0,
  sd_non = 0.1
)

Value

ssvsinput object

Arguments

y: Time series data of which columns indicate the variables.
ord: Order for VAR or VHAR.
type: Model type (Default: VAR or VHAR).
param: Preselected constants $c_0 << c_1$. By default, 0.1 and 10 (See Details).
include_mean: Add constant term (Default: TRUE) or not (FALSE).
gamma_param: Parameters (shape, rate) for Gamma distribution. This is for the output.
mean_non: Prior mean of unrestricted coefficients. This is for the output.
sd_non: Standard deviance of unrestricted coefficients. This is for the output.

Details

Instead of using subjective values of $(\tau_{0i}, \tau_{1i})$, we can use $$\tau_{ki} = c_k \hat{VAR(OLS)}$$ It must be $c_0 << c_1$.

In case of $(\omega_{0ij}, \omega_{1ij})$, $$\omega_{kij} = c_k = \hat{VAR(OLS)}$$ similarly.

References

George, E. I., & McCulloch, R. E. (1993). Variable Selection via Gibbs Sampling. Journal of the American Statistical Association, 88(423), 881-889.

George, E. I., Sun, D., & Ni, S. (2008). Bayesian stochastic search for VAR model restrictions. Journal of Econometrics, 142(1), 553-580.

Koop, G., & Korobilis, D. (2009). Bayesian Multivariate Time Series Methods for Empirical Macroeconomics. Foundations and Trends® in Econometrics, 3(4), 267-358.