STD: A Seasonal-Trend-Dispersion Decomposition of Time Series
This work addresses a gap in time series decomposition methods for fields relying on forecasting and decision-making, though it appears incremental by focusing on variance handling.
The authors tackled the problem of time series decomposition by addressing the neglect of variance properties in existing methods, proposing a seasonal-trend-dispersion (STD) decomposition that handles heteroscedasticity and includes components for trend, seasonality, and dispersion, with applications shown for analysis and forecasting.
The decomposition of a time series is an essential task that helps to understand its very nature. It facilitates the analysis and forecasting of complex time series expressing various hidden components such as the trend, seasonal components, cyclic components and irregular fluctuations. Therefore, it is crucial in many fields for forecasting and decision processes. In recent years, many methods of time series decomposition have been developed, which extract and reveal different time series properties. Unfortunately, they neglect a very important property, i.e. time series variance. To deal with heteroscedasticity in time series, the method proposed in this work -- a seasonal-trend-dispersion decomposition (STD) -- extracts the trend, seasonal component and component related to the dispersion of the time series. We define STD decomposition in two ways: with and without an irregular component. We show how STD can be used for time series analysis and forecasting.