get_edist-methods

get_edist,MixAR-method

get_edist,MixARGaussian-method

get_edist,MixARgen-method

Methods for function <code>get_edist</code> in package mixAR

methods

Model time series using mixture autoregressive (MAR)
models. Implemented are frequentist (EM) and Bayesian
methods for estimation, prediction and model
evaluation. See Wong and Li (2002)
<doi:10.1111/1467-9868.00222>, Boshnakov (2009)
<doi:10.1016/j.spl.2009.04.009>), and the extensive
references in the documentation.

Georgi Boshnakov

mixAR

Mixture Autoregressive Models

Davide Ravagli

get_edist-methods function

<code>get_edist</code> gives the error (or noise) distribution of MixAR
 objects.
Currently the distribution is returned as a list of functions. The
 list contains one element for each component. If the error
 distributions of all components are the same, then the list may
 contain a single element representing the common error distribution.
Note that the distribution is not necessarily stored in slot
 <code>dist</code> in this format, see the description of this slot in class
 <code>"MixARgen"</code>.
 Such a slot may even not exist if the distribution of the error
 components is fixed as is the case for class <code>MixARGaussian</code>.
Each subclass of <code>MixAR</code> needs to define a method for
 <code>get_edist</code>.<dl> <dt><code>signature(model = "MixAR")</code></dt>
<dd>Issue an error message and stop.
This method is invoked for subclasses of <code>MixAR</code> that have
 not defined their own method for <code>get_edist</code>. This is an
 error.
</dd>
 <dt><code>signature(model = "MixARGaussian")</code></dt>
<dd>Return an object representing the fact that the error
 distributions of the components of <code>MixARGaussian</code> objects
 are standard normal.</dd>
 <dt><code>signature(model = "MixARgen")</code></dt>
<dd>Return an object representing the error distributions of the
 components of <code>MixARgen</code> objects. The distributions are not
 necessarilly the same for such objects.</dd>
</dl>

Methods

Methods for function get_edist in package mixAR — get_edist-methods

<code>get_edist</code> gives the error (or noise) distribution of MixAR
 objects.
Currently the distribution is returned as a list of functions. The
 list contains one element for each component. If the error
 distributions of all components are the same, then the list may
 contain a single element representing the common error distribution.
Note that the distribution is not necessarily stored in slot
 <code>dist</code> in this format, see the description of this slot in class
 <code>"MixARgen"</code>.
 Such a slot may even not exist if the distribution of the error
 components is fixed as is the case for class <code>MixARGaussian</code>.
Each subclass of <code>MixAR</code> needs to define a method for
 <code>get_edist</code>.

<dl>

 <dt><code>signature(model = "MixAR")</code></dt>
<dd>Issue an error message and stop.
This method is invoked for subclasses of <code>MixAR</code> that have
 not defined their own method for <code>get_edist</code>. This is an
 error.
</dd>


 <dt><code>signature(model = "MixARGaussian")</code></dt>
<dd>Return an object representing the fact that the error
 distributions of the components of <code>MixARGaussian</code> objects
 are standard normal.</dd>


 <dt><code>signature(model = "MixARgen")</code></dt>
<dd>Return an object representing the error distributions of the
 components of <code>MixARgen</code> objects. The distributions are not
 necessarilly the same for such objects.</dd>


</dl>

get_edist-methods: Methods for function `get_edist` in package mixAR

Description

Arguments

Methods