A Comparative Analysis of the D041 Single Moving Average and other Time Series Analysis Forecasting Techniques.

摘要

This thesis examines the forecasting technique used in the Air Force Logistics Command D041 reparable asset management system. The process of retrieving usable data from the D041 Data Bank is described in some detail, including computer problems and potential pitfalls. It was hypothesized that the mean of the absolute values of the D041 forecast error was equal to zero. This hypothesis could not be rejected, but the results are questionable because after the fact forecasts were used. It was further hypothesized that another time series forecasting technique (exponential smoothing) would also yield an error distribution with a mean of zero. This hypothesis could not be rejected; however, the variance for the exponential smoothing forecast error distributions were less than the D041 forecast error distributions for all four lead times examined (one, two, three and four quarters). (Author)