Monitoring multivariate time series
Monitoring multivariate time series
复制标题
DOI：
10.1016/j.jmva.2016.12.003
复制
发表时间：
2017-03-01
影响因子：
1.6
通讯作者：
Hoga, Yannick
中科院分区：
文献类型：
--
作者：
Hoga, Yannick
我们推导出在线监测累积和（CANUUM）程序的多变量时间序列中的变点。这些程序依赖于最近的进展，尖锐的多元强不变性原则。理论结果表明，通过监测多元时间序列而不是仅监测其一个分量，可以提高功率并缩短检测时间。为了避免估计长期协方差矩阵的问题，我们采用了比率型检测器。使用这种方法，模拟表明，理论（渐近）的优势，也显示在有限的样本。对标准普尔500指数对数回报的实证应用表明，更快的检测也可以具有经济意义。(C)2016 Elsevier Inc. All rights reserved.
We derive online-monitoring cumulative sum (CUSUM) procedures for change points in multivariate time series. These procedures rely on recent advances in sharp multivariate strong invariance principles. Theoretical results show gains in power and shorter detection times to result from monitoring a multivariate time series instead of just one of its components. To sidestep the issue of estimating long-run covariance matrices, we employ a ratio-type detector. Using this approach, simulations show that the theoretical (asymptotic) advantages also show up in finite samples. An empirical application to S&P 500 log returns shows that the faster detection can also be economically significant. (C) 2016 Elsevier Inc. All rights reserved.