Home / Statistical Tools / Analysis Tools / Time Series / Double Exponential Smoothing
Double Exponential Smoothing¶
Smooth and forecast a series that has a trend, using Holt's method.
Where to find it
QXL Stat Tools → Analysis Tools → Time Series → Double Exponential Smoothing
What it does¶
Double exponential smoothing tracks two components as it walks through the series: the current level and the current trend. Each new observation updates both, weighted by the two smoothing constants. Because it carries a trend component, it follows trending data better than a moving average and can project forecasts forward.
Options¶
The dialog is Time Series Smoothing, with a Data tab and an Options tab.
Data tab
- Excel / GroupBy: analyze flat Excel columns, or split by one or more GroupBy columns
- Data Columns: one or more numeric columns; each produces its own analysis
- Overlay Datasets on a Single Chart: combine the selected series into one chart
Options tab (Double Exp Smoothing Options)
- Level (Alpha): smoothing constant for the level. Default 0.2; allowed 0 to 1 (entries outside the range are clamped). Larger values react faster to changes but smooth less.
- Trend (Gamma): smoothing constant for the trend. Default 0.2; allowed 0 to 1.
- Number of Forecasts: how many periods to forecast past the data. Default 0; must be 0 or more.
Output¶
A worksheet named DblExp ... containing:
- A line chart with the Actual, Fitted, and (when forecasting) Forecast series over the observation Index
- A data table with Index, Actual, Smooth, Predicted, Error columns
- An Accuracy Measures table with MAPE, MAD, and MSD