摘要:
本文分别运用聚合和分解的方法对预测需求总量的准确性进行对比,以确定采用何种方法预测移动通信需求量更为准确有效。在建立预测移动通信需求量的面板数据模型后,以预测全国移动通信用户数作为案例进行实证分析。研究表明,就汇总变量预测的平均绝对百分误差来说,分解方法优于聚合方法。此外,本文进一步研究了分解信息对移动通信需求总量预测准确性的影响,不仅分析了预测汇总变量的聚合与分解方法的预测表现,也分析了建立在分解预测基础上的类分解方法的预测表现。
Abstract: The paper uses the aggregation and disaggregation method separately to compare the accuracy of the forecast, in order to determine which method of forecasting the mobile communications demand is more accurate and effective. Panel data model is established to forecast the mobile communications demand and an empirical analysis is made based on forecasting the number of nationwide mobile communications users. The results show that the disaggregate approach outperforms the aggregate forecasting approach in terms of the mean absolute forecast errors of its demand predictions. Besides, this paper focuses on exploring the effect of disaggregate information on the accuracy of aggregate mobile communications demand forecasts. The paper also argues that the relative performances of aggregate and disaggregate approaches might depend on the specifics of the forecasting exercise, along with the performances of other approaches that are based on disaggregate approaches between these two extremes.