random_covmat

<code>random_covmat</code> generates random VAR model $(dxd)$ error term covariance matrix $\Omega$
 from (scaled) Wishart distribution.

internal

Maximum likelihood estimation of smooth transition vector
autoregressive models with various types of transition weight functions,
conditional distributions, and identification methods. Constrained
estimation with various types of constraints is available. Residual based
model diagnostics, forecasting, simulations, and calculation of impulse
response functions, generalized impulse response functions, and generalized
forecast error variance decompositions. See
Heather Anderson, Farshid Vahid (1998) <doi:10.1016/S0304-4076(97)00076-6>,
Helmut Lütkepohl, Aleksei Netšunajev (2017) <doi:10.1016/j.jedc.2017.09.001>,
Markku Lanne, Savi Virolainen (2024) <doi:10.48550/arXiv.2403.14216>,
Savi Virolainen (2024) <doi:10.48550/arXiv.2404.19707>.

Savi Virolainen

sstvars

Toolkit for Reduced Form and Structural Smooth Transition Vector
Autoregressive Models

random_covmat function

<dl><dt>omega_scale</dt>
<dd>a size $(dx1)$ strictly positive vector specifying the scale and variability of the
random covariance matrices in random mutations. The covariance matrices are drawn from (scaled) Wishart
distribution. Expected values of the random covariance matrices are <code>diag(omega_scale)</code>. Standard
deviations of the diagonal elements are <code>sqrt(2/d)*omega_scale[i]</code>
and for non-diagonal elements they are <code>sqrt(1/d*omega_scale[i]*omega_scale[j])</code>.
Note that for <code>d&gt;4</code> this scale may need to be chosen carefully. Default in <code>GAfit</code> is
<code>var(stats::ar(data[,i], order.max=10)$resid, na.rm=TRUE), i=1,...,d</code>. This argument is ignored if
<code>cond_dist == "ind_Student"</code>.</dd></dl>

Arguments

Create random VAR model error term covariance matrix — random_covmat

<dl>

<dt>omega_scale</dt>
<dd>a size $(dx1)$ strictly positive vector specifying the scale and variability of the
random covariance matrices in random mutations. The covariance matrices are drawn from (scaled) Wishart
distribution. Expected values of the random covariance matrices are <code>diag(omega_scale)</code>. Standard
deviations of the diagonal elements are <code>sqrt(2/d)*omega_scale[i]</code>
and for non-diagonal elements they are <code>sqrt(1/d*omega_scale[i]*omega_scale[j])</code>.
Note that for <code>d&gt;4</code> this scale may need to be chosen carefully. Default in <code>GAfit</code> is
<code>var(stats::ar(data[,i], order.max=10)$resid, na.rm=TRUE), i=1,...,d</code>. This argument is ignored if
<code>cond_dist == "ind_Student"</code>.</dd>

</dl>

random_covmat: Create random VAR model error term covariance matrix

Description

Usage

Value

Arguments