The forecast error needs to be calculated using actual sales as a base. There are several forms of forecast error calculation methods used, namely [[Mean percentage error|Mean Percent Error]], [[Root mean squared error|Root Mean Squared Error]], [[Tracking signal|Tracking Signal]] and [[Forecast bias|Forecast Bias]].
The demand patterns observed for some intermittent data and the estimated [[R square value]] in some case suggests that a straight line cannot be fitted as the errors incurred are very high.Moreover, from the mean absolute deviation we can interpret that the demand patterns for [[intermittent demand]] fails to follow normal distribution. So, standard statistical forecasting methods are not applicable to intermittent demand case which states that there is a need of developing a special mathematical model for this kind of inventory or altogether designing a new algorithm which will suggest optimum stocking and controlling policies resulting in minimum inventory cost.
Study of Bias Associated with forecasting of Intermittent Demands. Available from: https://www.researchgate.net/publication/309731283_Study_of_Bias_Associated_with_forecasting_of_Intermittent_Demands [accessed Jan 17, 2017].
