| TESTING FOR OUTLIERS IN TIME SERIES USING WAVELETS |
| |
| 作者姓名： | ZHANGTong ZHANGXibin ZHANGShiying |
| |
| 作者单位： | [1]SchoolofManagement,TianjinUniversity,Tianjin300072,China [2]SchoolofManagement,TianjinUniversity,Tianjin300072,China;DepartmentofEconometricsandBusinessStatistics,MonashUniversity,Clayton,Victoria3800,Australia |
| |
| 基金项目： | This research is supportea by the National Natural Science Foundation of China (79800012,70171001) |
| |
| 摘 要： | One remarkable feature ofwavelet decomposition is that the wavelet coefficients are localized, and any singularity in the input signals can only affect the wavelet coefficients at the point near the singularity. The localized property of the wavelet coefficients allows us to identify the singularities in the input signals by studying the wavelet coefficients at different resolution levels. This paper considers wavelet-based approaches for the detection of outliers in time series. Outliers are high-frequency phenomena which are associated with the wavelet coefficients with large absolute values at different resolution levels. On the basis of the first-level wavelet coefficients, this paper presents a diagnostic to identify outliers in a time series. Under the null hypothesis that there is no outlier, the proposed diagnostic is distributed as a X1^2. Empirical examples are presented to demonstrate the application of the proposed diagnostic.
|
| 关 键 词： | 时间序列分析 逸出值 小波分析 小波分解 小波系数 数据获得过程 |
TESTING FOR OUTLIERS IN TIME SERIES USING WAVELETS |
| |
| ZHANGTong ZHANGXibin ZHANGShiying.TESTING FOR OUTLIERS IN TIME SERIES USING WAVELETS[J].Journal of Systems Science and Complexity,2003,16(4):453-465. |
| |
| Authors: | ZHANG Tong |
| |
| Abstract: | One remarkable feature of wavelet decomposition is that the wavelet coefficients are localized, and any singularity in the input signals can only affect the wavelet coefficients at the point near the singularity. The localized property of the wavelet coefficients allows us to identify the singularities in the input signals by studying the wavelet coefficients at different resolution levels. This paper considers wavelet-based approaches for the detection of outliers in time series. Outliers are high-frequency phenomena which are associated with the wavelet coefficients with large absolute values at different resolution levels. On the basis of the first-level wavelet coefficients, this paper presents a diagnostic to identify outliers in a time series. Under the null hypothesis that there is no outlier, the proposed diagnostic is distributed as a x21 Empirical examples are presented to demonstrate the application of the proposed diagnostic. |
| |
| Keywords: | Outliers wavelet decomposition wavelet coefficients |
| 本文献已被 CNKI 维普 等数据库收录！ |
