Single
parameter exponential smoothing (Unadjusted) is an easy to implement method of
smoothing that overcomes some of the problems associated with moving
averages. In contrast to moving
averages, exponential smoothing permits the research to weight
observations. It is not unusual for recent
observations to contain more relevant information for forecasting purposes than
older ones. The method also generates
self-correcting forecasts through its ability to produce forecast values that
reflect adjustment for earlier errors.
Ft+1 = (alpha)Dt + (1 - (alpha))Ft-1
where: 0.0
<= alpha => 1.0
Fo = D1 or user input.
From
the above equations it is apparent that there are two specific data input
required for the unadjusted option.
These are:
1 Alpha; where alpha is between 0 and 1 is associated with exponential adjustments to the permanent component (new value) of the next period forecast.
2 Time Period: 1, 4, or 12.
3 Initial Base Value for Time Series - optional.
4 Number of Periods over which to forecast.