BigVAR.intermediate

BigVAR.intermediate-class

It inherits the class BigVAR, and contains the results from rolling validation

Estimates VAR and VARX models with Structured Penalties using the methods developed by Nicholson et al (2017)<doi:10.1016/j.ijforecast.2017.01.003> and Nicholson et al (2020) <doi:10.48550/arXiv.1412.5250>.

Will Nicholson

BigVAR

Dimension Reduction Methods for Multivariate Time Series

David Matteson

Jacob Bien

Ines Wilms

BigVAR.intermediate function

<dl>
<dt><code>ZFull</code></dt>
<dd>List containing full lag matrix and time series</dd></dl>
<dt><code>InSampMSFE</code></dt>
<dd>In-sample MSFE from optimal value of lambda</dd>
<dt><code>LambdaGrid</code></dt>
<dd>Grid of candidate lambda values</dd>
<dt><code>index</code></dt>
<dd>Index order of optimal lambda value</dd>
<dt><code>OptimalLambda</code></dt>
<dd>Value of lambda that minimizes MSFE</dd>
<dt><code>Data</code></dt>
<dd>a \(T \times k\) or \(T\times k + m\) multivariate time Series</dd>
<dt><code>lagmax</code></dt>
<dd>Maximal lag order</dd>
<dt><code>Structure</code></dt>
<dd>Penalty structure</dd>
<dt><code>Relaxed</code></dt>
<dd>Indicator for relaxed VAR</dd>
<dt><code>Granularity</code></dt>
<dd>Granularity of penalty grid</dd>
<dt><code>horizon</code></dt>
<dd>Desired forecast horizon</dd>
<dt><code>crossval</code></dt>
<dd>Cross-Validation procedure</dd>
<dt><code>alpha</code></dt>
<dd>additional penalty parameter for Sparse Lag Group or Sparse Own/Other methods. Will contain either the heuristic choice of \(1/(k+1)\) or the value selected by cross validation if the argument <code>dual</code> is set to <code>TRUE</code></dd>
<dt><code>Minnesota</code></dt>
<dd>Minnesota Prior Indicator</dd>
<dt><code>verbose</code></dt>
<dd>verbose indicator</dd>
<dt><code>dual</code></dt>
<dd>indicator as to whether dual cross validation was conducted</dd>
<dt><code>contemp</code></dt>
<dd>indicator if contemporaneous exogenous predictors are used</dd>

Fields

Author

BigVAR.intermediate
This class contains the in-sample results for cv.BigVAR — BigVAR.intermediate

<dl>
<dt><code>ZFull</code></dt>
<dd>List containing full lag matrix and time series</dd>


<dt><code>InSampMSFE</code></dt>
<dd>In-sample MSFE from optimal value of lambda</dd>


<dt><code>LambdaGrid</code></dt>
<dd>Grid of candidate lambda values</dd>


<dt><code>index</code></dt>
<dd>Index order of optimal lambda value</dd>


<dt><code>OptimalLambda</code></dt>
<dd>Value of lambda that minimizes MSFE</dd>


<dt><code>Data</code></dt>
<dd>a \(T \times k\) or \(T\times k + m\) multivariate time Series</dd>


<dt><code>lagmax</code></dt>
<dd>Maximal lag order</dd>


<dt><code>Structure</code></dt>
<dd>Penalty structure</dd>


<dt><code>Relaxed</code></dt>
<dd>Indicator for relaxed VAR</dd>


<dt><code>Granularity</code></dt>
<dd>Granularity of penalty grid</dd>


<dt><code>horizon</code></dt>
<dd>Desired forecast horizon</dd>


<dt><code>crossval</code></dt>
<dd>Cross-Validation procedure</dd>


<dt><code>alpha</code></dt>
<dd>additional penalty parameter for Sparse Lag Group or Sparse Own/Other methods. Will contain either the heuristic choice of \(1/(k+1)\) or the value selected by cross validation if the argument <code>dual</code> is set to <code>TRUE</code></dd>


<dt><code>Minnesota</code></dt>
<dd>Minnesota Prior Indicator</dd>


<dt><code>verbose</code></dt>
<dd>verbose indicator</dd>


<dt><code>dual</code></dt>
<dd>indicator as to whether dual cross validation was conducted</dd>


<dt><code>contemp</code></dt>
<dd>indicator if contemporaneous exogenous predictors are used</dd>


</dl>

BigVAR.intermediate: BigVAR.intermediate This class contains the in-sample results for cv.BigVAR

Description

Arguments

Fields

Author