tsspec.tsissm.estimate

tsspec

Extracts a model specification (class &#8220;tsissm.spec&#8221;) from
an object of class &#8220;tsissm.estimate&#8221;.

Unobserved components time series model using the linear innovations state space representation (single source of error) with choice of error distributions and option for dynamic variance. Methods for estimation using automatic differentiation, automatic model selection and ensembling, prediction, filtering, simulation and backtesting. Based on the model described in Hyndman et al (2012) <doi:10.1198/jasa.2011.tm09771>.

Alexios Ghalanos

tsissm

Linear Innovations State Space Unobserved Components Model

Alexios Galanos

tsspec.tsissm.estimate function

<dl><dt>object</dt>
<dd>an object of class &#8220;tsissm.estimate&#8221;.</dd>
<dt>y</dt>
<dd>an optional new xts vector.</dd>
<dt>lambda</dt>
<dd>an optional lambda parameter for the Box Cox transformation (if
previously used).</dd>
<dt>xreg</dt>
<dd>an optional matrix of regressors.</dd>
<dt>parameters</dt>
<dd>whether to set the parameters to their initial values, &#8220;initial&#8221;
or the optimally estimated &#8220;optimal&#8221;.</dd>
<dt>...</dt>
<dd>not currently used.</dd></dl>

Arguments

Model Specification Extractor — tsspec.tsissm.estimate

<dl>

<dt>object</dt>
<dd>an object of class &#8220;tsissm.estimate&#8221;.</dd>


<dt>y</dt>
<dd>an optional new xts vector.</dd>


<dt>lambda</dt>
<dd>an optional lambda parameter for the Box Cox transformation (if
previously used).</dd>


<dt>xreg</dt>
<dd>an optional matrix of regressors.</dd>


<dt>parameters</dt>
<dd>whether to set the parameters to their initial values, &#8220;initial&#8221;
or the optimally estimated &#8220;optimal&#8221;.</dd>


<dt>...</dt>
<dd>not currently used.</dd>

</dl>

tsspec.tsissm.estimate: Model Specification Extractor

Description

Usage

Value

Arguments