orderident

<code>orderident</code> provides some (very ad-hoc) methods for identifying
the ordering of the factors after running the (unrestricted) MCMC
sampler by
ordering according to the argument <code>method</code>.

Markov chain Monte Carlo (MCMC) sampler for fully Bayesian estimation of latent factor stochastic volatility models with interweaving <doi:10.1080/10618600.2017.1322091>. Sparsity can be achieved through the usage of Normal-Gamma priors on the factor loading matrix <doi:10.1016/j.jeconom.2018.11.007>.

Gregor Kastner

factorstochvol

Bayesian Estimation of (Sparse) Latent Factor Stochastic
Volatility Models

Darjus Hosszejni

Luis Gruber

orderident function

<dl><dt>x</dt>
<dd>Object of class <code>'fsvdraws'</code>, usually resulting from a call
to <code>fsvsample</code>.</dd>
<dt>method</dt>
<dd>Methods currently supported:<ul>
<li><code>summean</code> Sort by sum of mean loadings (descending).</li>
<li><code>summeaninv</code> Sort by sum of mean loadings (ascending).</li>
<li><code>summeanabs</code> Sort by sum of mean absolute loadings (descending).</li>
<li><code>summed</code> Sort by sum of median loadings (descending).</li>
<li><code>summedinv</code> Sort by sum of median loadings (ascending).</li>
<li><code>summedabs</code> Sort by sum of median absolute loadings (descending).</li>
<li><code>maxmed</code> Sort by maximum median loadings (descending).</li>
<li><code>maxmedinv</code> Sort by maximum median loadings (ascending).</li>
<li><code>maxmedrel</code> Sort by maximum median loadings, relative to the sum of all median loadings on that factor (descending).</li>
<li><code>maxmedabsrel</code> Sort by maximum absolute median loadings, relative to the sum of all median loadings on that factor (descending).</li>
</ul></dd></dl>

Arguments

A posteriori factor order identification — orderident

<dl>

<dt>x</dt>
<dd>Object of class <code>'fsvdraws'</code>, usually resulting from a call
to <code>fsvsample</code>.</dd>


<dt>method</dt>
<dd>Methods currently supported:<ul>
<li><code>summean</code> Sort by sum of mean loadings (descending).</li>
<li><code>summeaninv</code> Sort by sum of mean loadings (ascending).</li>
<li><code>summeanabs</code> Sort by sum of mean absolute loadings (descending).</li>
<li><code>summed</code> Sort by sum of median loadings (descending).</li>
<li><code>summedinv</code> Sort by sum of median loadings (ascending).</li>
<li><code>summedabs</code> Sort by sum of median absolute loadings (descending).</li>
<li><code>maxmed</code> Sort by maximum median loadings (descending).</li>
<li><code>maxmedinv</code> Sort by maximum median loadings (ascending).</li>
<li><code>maxmedrel</code> Sort by maximum median loadings, relative to the sum of all median loadings on that factor (descending).</li>
<li><code>maxmedabsrel</code> Sort by maximum absolute median loadings, relative to the sum of all median loadings on that factor (descending).</li>
</ul></dd>

</dl>

orderident: A posteriori factor order identification

Description

Usage

Value

Arguments

See Also