mixAR_cond_probs

Compute conditional probabilities for the E-step of the EM
 algorithm for MixAR models. Internal function.

 EM 

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

mixAR_cond_probs function

<dl> <dt>model</dt>
<dd>an object from a sub-class of "MixAR".</dd> <dt>y</dt>
<dd>the time series, a numeric vector.</dd> <dt>indx</dt>
<dd>indices of elements for which to compute residuals.</dd></dl>

Arguments

The E-step of the EM algorithm for MixAR models — mixAR_cond_probs

<dl>

 <dt>model</dt>
<dd>an object from a sub-class of "MixAR".</dd>

 <dt>y</dt>
<dd>the time series, a numeric vector.</dd>

 <dt>indx</dt>
<dd>indices of elements for which to compute residuals.</dd>

</dl>

mixAR_cond_probs: The E-step of the EM algorithm for MixAR models

Description

Usage

Value

Arguments

Details