smart_impactmat: Create a random VAR model (dxd) error impact matrix B fairly...

In sstvars: Toolkit for Reduced Form and Structural Smooth Transition Vector Autoregressive Models

Create a random VAR model (dxd) error impact matrix B fairly close to the given invertible impact matrix.

Description

smart_impactmat generates a random VAR model (dxd) error impact matrix B fairly close to the given invertible impact matrix.

Usage

smart_impactmat(d, B, accuracy, is_regime1 = TRUE)

Arguments

B	an invertible (dxd) impact matrix specifying expected value of the matrix to be generated. Should have strictly positive diagonal entries in a decreasing order.
accuracy	a positive real number adjusting how close to the given impact matrix the returned individual should be. Larger value implies higher accuracy.
is_regime1	is the impact matrix for Regime 1? Regime 1 impact matrix is constrained so the elements in its first row are in a decreasing ordering and the diagonal elements are strictly positive.

Value

Returns a (d^2 \times 1) vector containing the vectorized impact matrix B.

sstvars documentation built on April 11, 2025, 5:47 p.m.