tsensemble: Ensembles predictions using their posterior predictive or...

In tsmodels/tsmethods: Time Series Methods

Ensembles predictions using their posterior predictive or simulated distribution

Description

Generic method for ensembles of posterior predictive or simulated distributions spanning the same forecast horizon.

Usage

## S3 method for class 'ensemble.spec'
tsensemble(object, weights = NULL, ...)

tsensemble(object, weights = NULL, ...)

Arguments

object	currently only dispatches based on objects of class “ensemble.spec” which have been validated for ensembling.
weights	a numeric vector of length equal to the length of the ensembling predictions which represent the ensembling weights.
...	additional parameters passed to the method.

Details

Returns the weighted distribution, under the assumption that the predictions were generated using a joint error distribution whose values were passed to the innov argument of the predict function used for each model.

Value

An object of class “tsmodel.predict” or “tsmodel.distribution” depending on the input class in ensemble_modelspec.

The ensembled distribution.

tsmodels/tsmethods documentation built on Nov. 17, 2024, 12:34 a.m.