摘要
本文尝试将组合预测法应用于我国交通能源需求量的预测,以提高预测精度.通过赋予合理权重,将误差修正模型、非线性回归模型和多元回归模型加权组合建立组合预测模型.对各模型进行平均绝对百分误差(MAPE)、希尔不等系数(TheilIC)和均方根误差(RMSE)等指标的比较,证明单一模型经过组合能够提高预测精度.
This paper attempts to apply combination forecasting model into the prediction of Chinag traffic energy demand, aimed at improving forecasting accuracy. A new model, properly weighted, was established, combining such models as error correction model, nonlinear regression model and multiple regression models. All the models were compared in terms of mean absolute percent error （ MAPE）, Theilg Inequality Coefficients, RMS error. The results proved that combination forecasting model is able to improve prediction accuracy.
出处
《南京工程学院学报（自然科学版）》
2008年第2期62-66,共5页
Journal of Nanjing Institute of Technology(Natural Science Edition)
关键词
交通能源需求量
组合预测模型
误差修正模型
非线性回归模型
多元回归模型
demand of traffic energy
combination forecasting model
error correction model
nonlinear regression model
muhiple regression models
