组合预测模型在北京市汽车拥有量预测中的应用

摘要

In this paper ,several single forecasting methods are integrated to get a combinedforecasting method which is based on the combination of theil coefficient and the induced ordered weighted geometric averaging (IO-WGA ) operator .And the conception of superior combination forecasting is introduced .The forecasting of car owner-ship of Beijing is shown to illustrate the effectiveness.%将单项预测模型有机地结合，从相关性角度出发，各单项模型在各时点的权重系数与该时点的预测精度有关，得到了基于Theil不等系数的IOWGA算子组合模型，克服了传统组合预测的缺陷。介绍了相应的优性组合预测的概念，并利用该组合模型对北京市家用汽车拥有量进行预测，5种误差指标值均较低，说明了本文方法的有效性。