Learn R Programming
esreg (version 0.3.1)

vcov.esreg_twostep: Covariance Estimation for esreg_twostep

Description

Estimate the variance-covariance matrix of the joint (VaR, ES) estimator either using the asymptotic formulas or using the bootstrap.

Usage

# S3 method for esreg_twostep
vcov(object, sparsity = "iid", cond_var = "ind",
  bandwidth_type = "Hall-Sheather", bootstrap_method = NULL, B = 1000,
  block_length = NULL, ...)

Arguments

object

An esreg object

sparsity

Sparsity estimator (default: iid), see density_quantile_function for more details.

  • iid - Piecewise linear interpolation of the distribution

  • nid - Hendricks and Koenker sandwich

cond_var

Conditional truncated variance estimator (default: ind), see conditional_truncated_variance for more details.

  • ind - Variance over all negative residuals

  • scl_N - Scaling with the normal distribution

  • scl_sp - Scaling with the kernel density function

bandwidth_type

Bofinger, Chamberlain or Hall-Sheather

bootstrap_method

(default: NULL)

  • NULL - Use the asymptotic estimator

  • iid - Apply the iid bootstrap (Efron, 1979)

  • stationary - Apply the stationary bootstrap (Politis & Romano, 1994)

B

Number of bootstrap iterations

block_length

Average block length for the stationary bootstrap

...

additional arguments