SECTION 13.5 Summary

• Moving-average forecast models use the average of the last observed values to forecast next period’s value. The number is called the span of the moving average. Larger values of result in a smoother model.
• By appropriately centering the moving-average computations, seasonal ratios can be computed to capture seasonal effects. Seasonally adjusted data can be obtained by dividing the original data by the seasonal ratios. Government agencies typically release seasonally adjusted data for economic time series.
• The forecast equation for the simple exponential smoothing model is a weighted average of last period’s observed value and last period’s forecasted value. The degree of smoothing is determined by the choice of a smoothing constant . Some practitioners restrict to the range of , but some software will allow for a range of .