sim_mvt

This function samples n x multi-dimensional t-random matrix.

Tools to model and forecast multivariate time series
including Bayesian Vector heterogeneous autoregressive (VHAR) model
by Kim & Baek (2023) (<doi:10.1080/00949655.2023.2281644>).
'bvhar' can model Vector Autoregressive (VAR), VHAR, Bayesian VAR (BVAR), and Bayesian VHAR (BVHAR) models.

Young Geun Kim

bvhar

Bayesian Vector Heterogeneous Autoregressive Modeling

Changryong Baek

sim_mvt function

<dl><dt>num_sim</dt>
<dd>Number to generate process.</dd>
<dt>df</dt>
<dd>Degrees of freedom.</dd>
<dt>mu</dt>
<dd>Location vector</dd>
<dt>sig</dt>
<dd>Scale matrix.</dd>
<dt>method</dt>
<dd>Method to compute \(\Sigma^{1/2}\).
Choose between <code>eigen</code> (spectral decomposition) and <code>chol</code> (cholesky decomposition).
By default, <code>eigen</code>.</dd></dl>

Arguments

Generate Multivariate t Random Vector — sim_mvt

<dl>

<dt>num_sim</dt>
<dd>Number to generate process.</dd>


<dt>df</dt>
<dd>Degrees of freedom.</dd>


<dt>mu</dt>
<dd>Location vector</dd>


<dt>sig</dt>
<dd>Scale matrix.</dd>


<dt>method</dt>
<dd>Method to compute \(\Sigma^{1/2}\).
Choose between <code>eigen</code> (spectral decomposition) and <code>chol</code> (cholesky decomposition).
By default, <code>eigen</code>.</dd>

</dl>

sim_mvt: Generate Multivariate t Random Vector

Description

Usage

Value

Arguments