标题:
山东省批发和零售业销售总额的预测——基于ARIMA模型Forecast of the Total Sales of Wholesale and Retail in Shandong Province—Based on ARIMA Model
作者:
马永娟
关键字:
ARIMA模型, 批发零售业, 销售总额预测, 时间序列分析Auto Regressive Integrated Moving Average Model, Wholesale and Retail Industry, Prediction of Total Sales, Time Series Analysis
期刊名称:
《Advances in Social Sciences》, Vol.5 No.4, 2016-08-31
摘要:
商品批发与零售业销售价格是影响人们生活水平的重要因素之一，因此对商品批发和零售业销售总额进行预测有着积极的意义，时间序列分析提供了一套具有科学依据的动态数据处理方法，就是通过对模型的分析研究去了解数据的内在结构和复杂特性，从而达到预测其发展趋势并进行必要的控制的目的。本文利用Box-Jenkins法的ARIMA模型，对1979~2014年山东省批发和零售业销售总额数据序列进行分析，建立了1979~2014年山东省批发和零售业销售总额的自回归移动平均模型ARIMA(0,1,6)。检验结果显示，ARIMA(0,1,6)模型对原始数据序列有着较好的拟合效果，可用于短期内山东省批发和零售业销售总额的预测，为政府部门制定经济计划提供依据和参考。根据建立的模型预测结果，山东省批发和零售业销售额在未来几年仍将保持较高的增长趋势。
The sales price of wholesale and retail of commodities is one of the important factors that affect people’s living standard. It has positive significance to forecast the total sales of the wholesale and retail of commodities. Time series analysis provides a suit of methods dealing with dynamic data with the scientific basis, namely with the analysis and investigation, we can constitutionally know the structure and complex character of the data, so we can achieve the purpose of forecasting its development trend and putting up essential control. In this paper, using the method of Box-Jen- kins ARMIA model, the date sequence of wholesale and retail sales from 1979 to 2014 of Shandong province is analyzed, the model of auto regressive integrated moving average ARIMA (0,1,6) was established. The results show that the ARIMA model has good fitting effects on the original data sequence. The prediction effect can be used for short-term prediction of the total sales of wholesale and retail in Shandong province. It provides a basis and reference for government departments to formulate economic plans. According to the results of the prediction model established, in Shandong province the wholesale and retail sales remain high growth trend in the coming years.