Parametric Bootstrap for the Vector Autoregressive Model Using Lasso Regularization

Parametric Bootstrap for the Vector Autoregressive Model Using Lasso Regularization

Usage

PBootVARLasso(data, p, B, burn_in, n_lambdas, crit, max_iter, tol)

Arguments

data

Numeric matrix. The time series data with dimensions t by k, where t is the number of observations and k is the number of variables.

p

Integer. The order of the VAR model (number of lags).

B

Integer. Number of bootstrap samples to generate.

burn_in

Integer. Number of burn-in observations to exclude before returning the results in the simulation step.

n_lambdas

Integer. Number of lambdas to generate.

crit

Character string. Information criteria to use. Valid values include "aic", "bic", and "ebic".

max_iter

Integer. The maximum number of iterations for the coordinate descent algorithm (e.g., max_iter = 10000).

tol

Numeric. Convergence tolerance. The algorithm stops when the change in coefficients between iterations is below this tolerance (e.g., tol = 1e-5).

Value

List with the following elements:

• est: Numeric matrix. Original Lasso estimate of the coefficient matrix.

• boot: Numeric matrix. Matrix of vectorized bootstrap estimates of the coefficient matrix.

See also

Other Fitting Autoregressive Model Functions: FitMLVARDynr(), FitMLVARMplus(), FitVARDynr(), FitVARLassoSearch(), FitVARLasso(), FitVARMplus(), FitVAROLS(), LambdaSeq(), ModelVARP1Dynr(), ModelVARP2Dynr(), OrigScale(), PBootVARExoLasso(), PBootVARExoOLS(), PBootVAROLS(), RBootVARExoLasso(), RBootVARExoOLS(), RBootVARLasso(), RBootVAROLS(), SearchVARLasso(), StdMat()

Author

Ivan Jacob Agaloos Pesigan

Examples

pb <- PBootVARLasso(
  data = dat_p2,
  p = 2,
  B = 5,
  burn_in = 20,
  n_lambdas = 10,
  crit = "ebic",
  max_iter = 1000,
  tol = 1e-5
)
str(pb)
#> List of 2
#>  $ est : num [1:3, 1:7] 0.79 1 1.067 0.342 0 ...
#>  $ boot: num [1:5, 1:21] 1.07 0.8 0.634 0.683 0.985 ...