stlboot: STL/Loess bootstrapping

In trnnick/TStools: Time Series Analysis Tools and Functions

Description

STL/Loess bootstrapping by Bergmeir, Hyndman and Benitez, 2014.

Usage

stlboot(ts,k=1,test.season=c(TRUE,FALSE),outplot=c(FALSE,TRUE))

Arguments

ts	Time series to bootstrap. Must be ts object.
k	Number of bootstraps.
test.season	If TRUE then test for presence of seasonality. If FALSE then all non-yearly are decomposed using STL, assuming seasonality.
outplot	If TRUE provide a plot of the bootstrapped series.

Value

ts.recon

Array of bootstrapped series. Each column is a time series.

Author(s)

Nikolaos Kourentzes

References

Bergmeir C., Hyndman R. J., Benitez J. M., Bagging Exponential Smoothing Methods using STL Decomposition and Box-Cox Transformation. 2014, Working Paper. http://robjhyndman.com/working-papers/bagging-ets/

See Also

stl, loess.

Examples

stlboot(referrals,k=20,outplot=TRUE)

trnnick/TStools documentation built on Sept. 14, 2019, 5:22 a.m.