initModel

This is an internal function that usually won't be called by users directly. It validates the model type and generates the corresponding list of parameters for the model.

An implementation of a number of Global Trend models for time series forecasting
that are Bayesian generalizations and extensions of some Exponential Smoothing models.
The main differences/additions include 1) nonlinear global trend, 2) Student-t error
distribution, and 3) a function for the error size, so heteroscedasticity. The methods
are particularly useful for short time series. When tested on the well-known M3 dataset,
they are able to outperform all classical time series algorithms. The models are fitted
with MCMC using the 'rstan' package.

Christoph Bergmeir

Rlgt

Bayesian Exponential Smoothing Models with Trend Modifications

Slawek Smyl

Erwin Wibowo

To Wang Ng

Xueying Long

Alexander Dokumentov

Daniel Schmidt

Trustees of Columbia University 

initModel function

<dl><dt>model.type</dt>
<dd>type of the forecasting model selected, a character object</dd>
<dt>use.regression</dt>
<dd>binary parameter indicating whether additional regressors will be used for forecasting in multivariate settings.</dd>
<dt>seasonalityMethodId</dt>
<dd>Seasonality method Id (0- HW, 1- generalized).</dd>
<dt>levelMethodId</dt>
<dd>Level method Id.</dd>
<dt>useSmoothingMethodForError</dt>
<dd>if the non-standard function for error size should be used, one based on smoothed innovations or surprises</dd></dl>

Arguments

Initialize a model from the Rlgt family — initModel

<dl>

<dt>model.type</dt>
<dd>type of the forecasting model selected, a character object</dd>


<dt>use.regression</dt>
<dd>binary parameter indicating whether additional regressors will be used for forecasting in multivariate settings.</dd>


<dt>seasonalityMethodId</dt>
<dd>Seasonality method Id (0- HW, 1- generalized).</dd>


<dt>levelMethodId</dt>
<dd>Level method Id.</dd>


<dt>useSmoothingMethodForError</dt>
<dd>if the non-standard function for error size should be used, one based on smoothed innovations or surprises</dd>

</dl>

initModel: Initialize a model from the Rlgt family

Description

Usage

Value

Arguments