摘要
针对复杂经济时间序列具有的非线性、非平稳、多尺度特性,文章提出一种基于多尺度事件识别的干预分析方法用于事件对复杂经济时间序列的影响分析。首先运用经验模态分解算法将原始序列按其构成特点分解到不同尺度,然后采用迭代累积平方和方法识别出不同序列分量的结构性变点,获取事件对序列影响的时间点,最后针对不同尺度的结构性变点,采用干预分析方法建立事件对序列影响的干预模型,定量分析事件对不同尺度序列的影响情况。
In view of the non-linear,non-stationary and multi-scale characteristics of complex economic time series,this paper proposes an intervention analysis method based on multi-scale event recognition to analyze the impact of events on complex economic time series.Firstly,the empirical mode decomposition(EMD)algorithm is used to decompose the original sequence to different scales according to its composition characteristics.Then the iterative cumulative sum of squares(ICSS)algorithm is used to identify the structural variation points of different sequence components and obtain the time points at which an event affects the sequence.Finally,according to the structural variation points of different scales,intervention analysis method is adopted to establish an intervention model for the impact of events on the sequence,and quantitatively analyze the impact of events on different scale sequences.
作者
蒋铁军
周成杰
张怀强
Jiang Tiejun;Zhou Chengjie;Zhang Huaiqiang(Department of Management Engineering and Equipment Economy,Naval University of Engineering,Wuhan 430033,China)
出处
《统计与决策》
CSSCI
北大核心
2019年第19期10-14,共5页
Statistics & Decision
基金
国家社会科学基金军事学项目(16GJ003-105)
中国博士后科学基金特别资助项目(2014T70742)
中国博士后科学基金面上资助项目(2013M542067)
海军工程大学科研自主立项项目(20161632)
关键词
事件分析
维修保障经费
经验模态分解
迭代累加平方和
干预分析
event analysis
maintenance and support fund
empirical mode decomposition
iterative cumulative sum ofsquares
intervention analysis