decompose a time series into level, residuals, and potentially trend and seasonal components
Decomposition(model, ts, extraparameters)
Exponential smoothing model
Time series consisting of a single data set
(optional) table of parameter values
The Decomposition command takes a time series and decomposes it according to an exponential smoothing model.
It returns a time series with two, three, or four data sets in it: one for the level, one for the residuals, if the model has a trend component then one data set for the trends, and if the model has a seasonal component then a data set for the seasonal component.
Consider the following time series. It represents international tourist visitor nights in Australia.
ts ≔ TimeSeries⁡41.7,24.0,32.3,37.3,46.2,29.3,36.5,43.0,48.9,31.2,37.7,40.4,51.2,31.9,41.0,43.8,55.6,33.9,42.1,45.6,59.8,35.2,44.3,47.9,startdate=2005,frequency=quarterly,header=Visitor nights
ts≔Time seriesVisitor nights24 rows of data:2005-Jan-01 - 2010-Oct-01
Fit an exponential smoothing model to it.
esm ≔ ExponentialSmoothingModel⁡ts
Create the decomposition. Since this is a model with both trend and seasonal components, you get four data sets.
dc ≔ Decomposition⁡esm,ts
dc≔Time seriesVisitor nights (residuals), ..., Visitor nights (seasonal)24 rows of data:2005-Jan-01 - 2010-Oct-01
Since the error and seasonal components are multiplicative, it makes sense to display them together. The trend and level components are displayed separately.
Hyndman, R.J. and Athanasopoulos, G. (2013) Forecasting: principles and practice. http://otexts.org/fpp/. Accessed on 2013-10-09.
Hyndman, R.J., Koehler, A.B., Ord, J.K., and Snyder, R.D. (2008) Forecasting with Exponential Smoothing: The State Space Approach. Springer Series in Statistics. Springer-Verlag Berlin Heidelberg.
The TimeSeriesAnalysis[Decomposition] command was introduced in Maple 18.
For more information on Maple 18 changes, see Updates in Maple 18.
Download Help Document