One of the basic principles of forecasting is that forecasts are rarely perfect. However, how does a manager know how much a forecast can be off the mark and still be reasonable? One of the most important criteria for choosing a forecasting model is its accuracy. Also, data can change over time, and a model that once provided good results may no longer be adequate. The model's accuracy can be assessed only if forecast performance is measured over time. For all these reasons it is important to track model performance over time, which involves monitoring forecast errors.
Forecast error is the difference between the forecast and actual value for a given period, or
where Et = forecast error for period t
At = actual value for period t
Ft = forecast for period t
Difference between forecast and actual value for a given period.
However, error for one time period does not tell us very much. We need to measure forecast accuracy over time. Two of the most commonly used error measures are the mean absolute deviation (MAD) and the mean squared error (MSE). MAD is the average of the sum of the absolute errors:
Mean absolute ...