Use double exponential smoothing to smooth the data in a time series, and to provide short-term forecasts. For example, you might want to predict the temperatures for the next 7 days using the data in a time series containing successive temperatures in a city over the past 50 days. Or you might want to predict the sales of a certain brand of cereals in a supermarket over the next 6 months using the sales data collected over 3 years.

Use double exponential smoothing when:

·    You have data with a constant or slightly varying trend.

·    You have data with no seasonal pattern.

·    The series does not include any missing values.

·    You want short term forecasting.

This procedure also serve as a general smoothing method.

You wish to predict computer sales over the next 6 months using data collected over the past 2 years (24 months). You also collected software sales data over the same time period.

Data: ComputerSales.MTW (available in the Sample Data folder).