This package contains enhancements to the stl
implementation that comes with base R. Ryan is making it public here.
Here are some of the added features over stl
done by Ryan Hafen:
- Can handle NA values
- Higher order loess smoothing (more than just local constant and linear)
- Automated parameter choices for local quadratic
- Plot methods for diagnostics
Here are some of the features done by Xiaosu Tong:
- Can pass a custom initial trend component
- Can pass a custom initial fc.first and fc.second components
For experimental inference, prediction, and variance reduction at endpoints, see the operator package.
- Cleveland, R. B., Cleveland, W. S., McRae, J. E., & Terpenning, I. (1990). STL: A seasonal-trend decomposition procedure based on loess. Journal of Official Statistics, 6(1), 3-73.
- Hafen, R. P. "Local regression models: Advancements, applications, and new methods." (2010).
library(devtools)
#Ryan's version
install_github("stl2", "hafen")
#Xiaosu's version
install_github("XiaosuTong/stl3")
This software is released under the BSD license. Please read the license document.