A statistic that reveals when parameter estimates in a forecasting model are not optimal. For example, a tracking signal might be based on a graph of the ratio of the cumulative sum of the differences between the actual and forecast values to the mean absolute deviation. If the tracking signal exceeds a certain value, the series can then be flagged for examination. This concept has been used successfully in quality control. It seems sensible also for forecasting, although little research supports its use. An alternative is to use successive reestimation.