多因素数据重心预测方法及应用研究

Study of Multi-Factor Data Barycenter Forecasting and Applications

本文基于数据重心概念,通过大量的研究和推导,提出数据重心参数估计理论,并利用数据重心法估计多项式回归预测模型的参数,应用于我国钢材消费量的预测。从应用的结果看,增加了我国目前钢材预测的方法。本方法能最大限度地平滑预测模型的误差,而且应用条件比最小二乘法宽松;也不会因为个别残差较大的异常点而对预测结果产生不稳定性,从而提高了拟合和预测的稳健度,计算更简捷。

A new and useful parameter estimation method was presented in light of the stability of gravity center of object in this paper.This method could deal with the fitting and forecasting of economy volume and could greatly decrease the errors of the fitting and forecasting results. Moreover, the strict hypothetical conditions in least squares method were not mecessary in the method presented in this paper, which overcame the shortcomings of least squares method and expanded the application of data barycentre method.Application to the steel consumption volume forecasting was presented in this paper. It is shown that the result of fitting and forecasting was satisfactory. From the comparison between data barycentre forecasting method and least squares method, we could conclude that the fitting and forecasting results using data barycentre method were more stable than that using least squares regression forecasting method, and the computation of data barycentre forecasting method was simpler than that of least squares method. As a result, the data barycentre method was convenient to use in technical economy.