季节性预测建模及其在短期宏观经济预测中的应用  

Seasonal Prediction Modeling and Its Application in Short-term Macroeconomic Prediction

作　　者：姜向荣 Jiang Xiangrong(Institute of Science and Technology for Development of Shandong,Qilu University of Technology,Jinan 250014,China)

机构地区：[1]齐鲁工业大学山东省科技发展战略研究所

出　　处：《统计与决策》2019年第16期75-78,共4页Statistics & Decision

基　　金：山东省科学院智库创新专项

摘　　要：文章构建了利用时间序列的季节变化规律进行短期预测的季节性预测模型。该模型的基本原理是对季节性建立基于已知观测值的季节末总量的条件分布,采用极大似然法对历史数据进行季节性参数估计;利用预测周期的部分观测值和已估计的季节性参数进行总量预测。通过实证分析,该模型对稳定季节性的时间序列具有较高的预测效率。This paper proposes a seasonal prediction model based on the seasonal variation pattern of time series to conduct short-term prediction.The basic principle of the model is to firstly establish the conditional distribution of the total accumulation at the end of the season based on the known observed values for seasonality,and then to use the maximum likelihood method to estimate the seasonal parameters on historical data,and finally to perform a total forecast by use of partial observations of the predicted period and the estimated seasonal parameters.The empirical analysis shows that the proposed model has relatively higher prediction efficiency for stable seasonal time series.

关 键 词：季节性 时间序列 预测 ARIMA模型 

分 类 号：F224[经济管理—国民经济]