TrendDecomposition.jl

TrendDecomposition.jl is a Julia package for decomposition of time series into trend and cycle components. More generally it provides both (stochastic) trend component estimation and forecasting, though not all methods are suitable for forecasting.

Documentation:

Functionality and Implemented Methods

The following is list of already implemented and documented methods:

• Exponential Smoothing

  • Simple exponential smoothing
  • Double exponential smoothing / Brown linear method
  • Holt Linear procedure
  • Holt Winters method

• Penalized smoothing

  • Bohlmann Filter / Whittaker-Henderson Smoothing
  • Leser / Hodrick-Prescott (HP) Filter
  • Boosted HP Filter

• Moving Average (MA)

• Seasonal Average

• Classical Decomposition by moving averages

Get Started

This package is now featured on the official general Julia package registry. Simply use Julia's package manager pkg to add TrendDecomposition to your preferred environment.

@(v1.11) pkg> add TrendDecomposition

julia> using TrendDecomposition

The developing branch of this package can either be employed by cloning this repository or by using the Julia package manager. With the package manager simply use the add command:

@(v1.11) pkg> add https://github.com/sdBrinkmann/TrendDecomposition.jl

Important

This package is currently under rapid development and follows Semantic Versioning. Until the 1.0.0 release is reached, the API of this package can change with any minor version update, please consult the documentation of this package after each update when using this package.