基于绝对误差的线性组合预测研究

Research on linear combination forecasting based on absolute error

针对组合预测效果评价中存在着把拟合精度和预测精度相混淆的问题,阐述了区分样本区间和预测区间的组合预测精度评价方法,并在预测区间上对2种常用的基于绝对误差的线性组合预测方法的预测精度进行了评价,对评价结果进行实例和理论分析。在此基础上,提出一种新的基于绝对误差的线性组合预测方法——基于预测模型有效性的线性组合预测方法。

In order to solve the problem of mixing fitting precision with forecasting precision in combination forecasting,the precision evaluation method for distinguishing forecasting interval from sample interval is expatiated.The forecasting precision of two common linear combination forecasting models based on absolute error are evaluated on forecasting interval,and the evaluating result is validated and analyzed.Based on above analysis,a new linear combination forecasting method based on the forecasting model＇s validity is proposed.