Decomposing of time series

From Wikipedia, the free encyclopedia

The Decomposing of time series is a statistical method that deconstructs a time series into its components. It is an important technique for time series analysis, especially for seasonal adjustment. Monthly or quarterly economic time series are usually composed of:

• • the Trend Component T_t that reflects the long dated progression of the series
  • the Cyclical Component C_t that describes regular fluctuations caused by the economic cycle
  • the Seasonal Component S_t reflecting seasonal fluctuations
  • the Irregular Component I_t(or “noise”) that describes random, irregular influences. Compared to the other components it represents the residuals of the time series.

Statistical Software for decomposing is e.g. the program BV4.1 that bases on the so-called berlin procedure.