pls: Prediction Likelihood Score

Description Usage Arguments Details Value Author(s) References Examples

View source: R/methods.R

Description

Function estimates Prediction Likelihood Score for the provided model

Usage

1
2
3
4
pls(object, holdout = NULL, ...)

## S3 method for class 'smooth'
pls(object, holdout = NULL, ...)

Arguments

object

The model estimated using smooth functions. This thing also accepts other models (e.g. estimated using functions from forecast package), but may not always work properly with them.

holdout

The values for the holdout part of the sample. If the model was fitted on the data with the holdout=TRUE, then the parameter is not needed.

...

Parameters passed to multicov function. The function is called in order to get the covariance matrix of 1 to h steps ahead forecast errors.

Details

Prediction likelihood score (PLS) is based on either normal or log-normal distribution of errors. This is extracted from the provided model. The likelihood based on the distribution of 1 to h steps ahead forecast errors is used in the process.

Value

A value of the log-likelihood.

Author(s)

Ivan Svetunkov, ivan@svetunkov.ru

References

distribution. IEEE Signal Processing Letters. 13 (5): 300-303. doi: 10.1109/LSP.2006.870353 - this is not yet used in the function.

Examples

1
2
3
4
5
6
# Generate data, apply es() with the holdout parameter and calculate PLS
x <- rnorm(100,0,1)
ourModel <- es(x, h=10, holdout=TRUE, interval=TRUE)
pls(ourModel, type="a")
pls(ourModel, type="e")
pls(ourModel, type="s", obs=100, nsim=100)

config-i1/smooth documentation built on June 16, 2021, 2:13 p.m.