Sequential Outlier Detection in Nonstationary Time Series
提出一种在非平稳时间序列中逐点检测异常值的新方法，通过极值理论控制连续检验的错误概率，并对比了统计与机器学习领域的最新方法。
ABSTRACT A novel method for sequential outlier detection in nonstationary time series is proposed. The method tests the null hypothesis of “no outlier” at each time point, addressing the multiple testing problem by bounding the error probability of successive tests, using extreme‐value theory. The asymptotic properties of the test statistic are studied under the null hypothesis and alternative hypothesis. The finite sample properties of the new detection scheme are investigated by means of a simulation study, and the method is compared with alternative procedures that have recently been proposed in the statistics and machine learning literature.