时序IO与AO型异常值稳健联合检测法及其应用
|
摘要
文章分析了基于假设检验的时间序列IO、AO型异常点检测法的不稳健性,并在此基础上构建了IO、AO型异常点稳健联合检测法。模拟和实证分析均表明:相比于传统检测法,提出的稳健联合检测法对异常点检测能力显著提高,并且能更好地捕捉到我国金融市场的异常特点。
This paper analyzes the non-robustness of time series IO and AO outlier detection methods based on hypothesis testing, on the basis of which a robust joint detection method of IO and AO outliers is constructed. Simulation and empirical study results show that compared with the traditional detection method, the proposed robust joint detection method can improve the outlier detection ability more significantly, and can better capture the anomalies of Chinese financial market.
This paper analyzes the non-robustness of time series IO and AO outlier detection methods based on hypothesis testing, on the basis of which a robust joint detection method of IO and AO outliers is constructed. Simulation and empirical study results show that compared with the traditional detection method, the proposed robust joint detection method can improve the outlier detection ability more significantly, and can better capture the anomalies of Chinese financial market.
引文
[1]Bruce A G,Martin R D.Leave-k-out Diagnostics for Time Series[J].Journal of the Royal Statistical Society,1989,51(3).
[2]Ljung G M.On Outlier Detection in Time Series[J].Journal of the Royal Statistical Society,1993,55(2).
[3]杨虎,李强.金融时序中异常数据挖掘算法设计及实证分析[J].中国管理科学,2004,12(3).
[4]孙建树,娄渊胜,陈裕俊.基于ARIMA-SVR的水文时间序列异常值检测[J].计算机与数字工程,2018,46(2).
[5]Carnero M A,Pe?a D,Ruiz E.Effects of Outliers on the Identification and Estimation of GARCH Models[J].Journal of Time Series Analysis,2007,28(4).
[6]GranéA,Veiga H.Wavelet Based Detection of Outliers in Financial Time Series[J].Computational Statistics and Data Analysis,2010,54(11).
[7]Cucina D,Salvatore A D,Protopapas M K.Outliers Detection in Multivariate Time Series Using Genetic Algorithms[J].Chemometrics&Intelligent Laboratory Systems,2014,132(8).
[8]Nossa L P,Angulo M Aá,Torres A.Detection of Outliers and Replacement of Missing Values for Water Quality UV-Vis Absorbance Time Series[J].Ingeniería,2017,22(1).
[9]王志坚,王斌会.一种改进的时间序列IO型异常值检测法[J].统计与决策,2014,(22).
[10]王志坚,王斌会.稳健改进的AO型异常点检测法在金融时序中的应用[J].数理统计与管理,2016,35(2).
[2]Ljung G M.On Outlier Detection in Time Series[J].Journal of the Royal Statistical Society,1993,55(2).
[3]杨虎,李强.金融时序中异常数据挖掘算法设计及实证分析[J].中国管理科学,2004,12(3).
[4]孙建树,娄渊胜,陈裕俊.基于ARIMA-SVR的水文时间序列异常值检测[J].计算机与数字工程,2018,46(2).
[5]Carnero M A,Pe?a D,Ruiz E.Effects of Outliers on the Identification and Estimation of GARCH Models[J].Journal of Time Series Analysis,2007,28(4).
[6]GranéA,Veiga H.Wavelet Based Detection of Outliers in Financial Time Series[J].Computational Statistics and Data Analysis,2010,54(11).
[7]Cucina D,Salvatore A D,Protopapas M K.Outliers Detection in Multivariate Time Series Using Genetic Algorithms[J].Chemometrics&Intelligent Laboratory Systems,2014,132(8).
[8]Nossa L P,Angulo M Aá,Torres A.Detection of Outliers and Replacement of Missing Values for Water Quality UV-Vis Absorbance Time Series[J].Ingeniería,2017,22(1).
[9]王志坚,王斌会.一种改进的时间序列IO型异常值检测法[J].统计与决策,2014,(22).
[10]王志坚,王斌会.稳健改进的AO型异常点检测法在金融时序中的应用[J].数理统计与管理,2016,35(2).