specify_bsvar_hmsh: R6 Class representing the specification of the BSVARHMSH...

In bsvars: Bayesian Estimation of Structural Vector Autoregressive Models

R6 Class representing the specification of the BSVARHMSH model with Heterogeneous Markov Switching Heteroskedasticity.

Description

The class BSVARHMSH presents complete specification for the BSVAR model with Heterogeneous Markov Switching Heteroskedasticity.

Public fields

p

a non-negative integer specifying the autoregressive lag order of the model.

identification

an object IdentificationBSVARs with the identifying restrictions.

prior

an object PriorBSVARMSH with the prior specification.

data_matrices

an object DataMatricesBSVAR with the data matrices.

starting_values

an object StartingValuesBSVARHMSH with the starting values.

finiteM

a logical value - if true a stationary Markov switching model is estimated. Otherwise, a sparse Markov switching model is estimated in which M=20 and the number of visited states is estimated.

Methods

Public methods

• BSVARHMSH$new()

• BSVARHMSH$get_normal()

• BSVARHMSH$get_data_matrices()

• BSVARHMSH$get_identification()

• BSVARHMSH$get_prior()

• BSVARHMSH$get_starting_values()

• BSVARHMSH$clone()

---

BSVARHMSH$new()

Create a new specification of the BSVAR model with Heterogeneous Markov Switching Heteroskedasticity, BSVARHMSH.

Usage

BSVARHMSH$new(
  data,
  p = 1L,
  M = 2L,
  B,
  A,
  distribution = c("norm", "t"),
  exogenous = NULL,
  stationary = rep(FALSE, ncol(data)),
  finiteM = TRUE
)

Arguments

data

a (T+p)xN matrix with time series data.

p

a positive integer providing model's autoregressive lag order.

M

an integer greater than 1 - the number of Markov process' heteroskedastic regimes.

B

a logical NxN matrix containing value TRUE for the elements of the structural matrix B to be estimated and value FALSE for exclusion restrictions to be set to zero.

A

a logical NxK matrix containing value TRUE for the elements of the autoregressive matrix A to be estimated and value FALSE for exclusion restrictions to be set to zero.

distribution

a character string specifying the conditional distribution of structural shocks. Value "norm" sets it to the normal distribution, while value "t" sets the Student-t distribution.

exogenous

a (T+p)xd matrix of exogenous variables.

stationary

an N logical vector - its element set to FALSE sets the prior mean for the autoregressive parameters of the Nth equation to the random walk process, otherwise to white noise.

finiteM

a logical value - if true a stationary Markov switching model is estimated. Otherwise, a sparse Markov switching model is estimated in which M=20 and the number of visited states is estimated.

Returns

A new complete specification for the bsvar model with Heterogeneous Markov Switching Heteroskedasticity, BSVARHMSH.

---

BSVARHMSH$get_normal()

Returns the logical value of whether the conditional shock distribution is normal.

Usage

BSVARHMSH$get_normal()

Examples

spec = specify_bsvar_hmsh$new(us_fiscal_lsuw)
spec$get_normal()

---

BSVARHMSH$get_data_matrices()

Returns the data matrices as the DataMatricesBSVAR object.

Usage

BSVARHMSH$get_data_matrices()

Examples

spec = specify_bsvar_hmsh$new(
   data = us_fiscal_lsuw,
   p = 4,
   M = 2
)
spec$get_data_matrices()

---

BSVARHMSH$get_identification()

Returns the identifying restrictions as the IdentificationBSVARs object.

Usage

BSVARHMSH$get_identification()

Examples

spec = specify_bsvar_hmsh$new(
   data = us_fiscal_lsuw,
   p = 4,
   M = 2
)
spec$get_identification()

---

BSVARHMSH$get_prior()

Returns the prior specification as the PriorBSVARMSH object.

Usage

BSVARHMSH$get_prior()

Examples

spec = specify_bsvar_hmsh$new(
   data = us_fiscal_lsuw,
   p = 4,
   M = 2
)
spec$get_prior()

---

BSVARHMSH$get_starting_values()

Returns the starting values as the StartingValuesBSVARHMSH object.

Usage

BSVARHMSH$get_starting_values()

Examples

spec = specify_bsvar_hmsh$new(
   data = us_fiscal_lsuw,
   p = 4,
   M = 2
)
spec$get_starting_values()

---

BSVARHMSH$clone()

The objects of this class are cloneable with this method.

Usage

BSVARHMSH$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

See Also

estimate, specify_posterior_bsvar_hmsh

Examples

spec = specify_bsvar_hmsh$new(
   data = us_fiscal_lsuw,
   p = 4,
   M = 2
)


## ------------------------------------------------
## Method `BSVARHMSH$get_normal()`
## ------------------------------------------------

spec = specify_bsvar_hmsh$new(us_fiscal_lsuw)
spec$get_normal()


## ------------------------------------------------
## Method `BSVARHMSH$get_data_matrices()`
## ------------------------------------------------

spec = specify_bsvar_hmsh$new(
   data = us_fiscal_lsuw,
   p = 4,
   M = 2
)
spec$get_data_matrices()


## ------------------------------------------------
## Method `BSVARHMSH$get_identification()`
## ------------------------------------------------

spec = specify_bsvar_hmsh$new(
   data = us_fiscal_lsuw,
   p = 4,
   M = 2
)
spec$get_identification()


## ------------------------------------------------
## Method `BSVARHMSH$get_prior()`
## ------------------------------------------------

spec = specify_bsvar_hmsh$new(
   data = us_fiscal_lsuw,
   p = 4,
   M = 2
)
spec$get_prior()


## ------------------------------------------------
## Method `BSVARHMSH$get_starting_values()`
## ------------------------------------------------

spec = specify_bsvar_hmsh$new(
   data = us_fiscal_lsuw,
   p = 4,
   M = 2
)
spec$get_starting_values()

bsvars documentation built on Aug. 22, 2026, 5:09 p.m.