A Cumulative Sum Algorithm for Detecting Changes in the Covariance Matrix of Multidimensional Time Series
Abstract
The problem of detecting spontaneous changes in the probabilistic characteristics (mismatching) of vector time series using the well-known cumulative sum algorithm (CUSUM) is considered. The case in which it is in the form of a stepwise change in the entries of the time series covariance matrix is studied. To solve this problem, it is proposed to use a preliminary linear transformation of the values of the observed time series, which ensures simultaneous transformation of the covariance matrix to the unity form before the change, and to the diagonal form after the change. Basic provisions that describe the corresponding detection algorithm and the relationships using which the above- mentioned linear transformation is implemented are given. It is shown that its application can significantly simplify the solution of matters concerned with synthesizing a control algorithm with the specified properties. This is due to the fact that the time series resulting from such transformation has uncorrelated components, and the changes boil down to deviation of the variances of these components from the original unity value.
For the two-dimensional case, the procedure for synthesizing the control algorithm is considered in detail. For its practical implementation, the calculation relations obtained using the simulation method are presented that make it possible to find the threshold of the control algorithm from the given value of the interval between false alarms and to estimate the average delay time in detecting a mismatch. An example of implementing such synthesis is presented, which illustrates the entire process of constructing a controlling procedure.
References
2. Никифоров И.В. Последовательное обнаружения изменения свойств временных рядов. М.: Наука, 1983.
3. Shafid A. Bibliometric Analysis of EWMA and CUSUM Control Chart Schemes // ITEE J. 2018. V. 7. Iss. 2. Pp. 1—11.
4. Ширяев А.Н. Задача скорейшего обнаружения нарушения стационарного режима // Доклады АН СCСР. 1961. Т. 138. № 5. С. 1039—1042.
5. Crosier R.B. Multivariate Generalizations of Cumulative Sum Quality-control Schemes // Technometrics. 1988. V. 30. Pp. 291—303.
6. Chan L.K., Zhang J. Сharts Cumulative Sum Control for the Covariance Matrix // Statistica Sinica. 2001. V. 11. Pp. 767—790.
7. Ngai H.M., Zhang J. Multivariate Cumulative Sum Control Charts Based on Projection Pursuit // Statistica Sinica. 2001. V. 11. Pp.747—766.
8. Runger, G.C., Testik M.C. Multivariate Extensions to Cumulative Sum Control Charts // Quality and Reliability Eng. Intern. 2004. V. 20. Pp. 587—606.
9. Yeh A.B., Lin D.K., McGrath R.N. Multivariate Control Chart for Monitoring Covariance Matrix: a Review // Quality Techn. & Quantitative Management. 2006. V. 3. Pp. 415—436.
10. Liu L., Zhong J., Ma Y. A Multivariate Synthetic Control Chart for Monitoring Covariance Matrix Based on Conditional Entropy // Proc. 19th Intern. Conf. Industrial Eng. and Eng. Management. Berlin: Springer, 2013. Pp. 99—107.
11. Филаретов Г.Ф., Червова А.А. Последовательный алгоритм обнаружения момента изменения дисперсии временного ряда // Заводская лаборатория. Диагностика материалов. 2019. Т. 85. № 3. С. 75—82.
12. Левин Б.Р. Теоретические основы статистической радиотехники. М.: Советское радио, 1975.
13. Айвазян С.А., Мхитарян В.С. Прикладная статистика и основы эконометрики. М.: ЮНИТИ, 1998.
---
Для цитирования: Филаретов Г.Ф., Симоненков П.С. Алгоритм кумулятивных сумм для обнаружения изменений ковариационной матрицы многомерных временных рядов // Вестник МЭИ. 2020. № 3. С. 92—101. DOI: 10.24160/1993-6982-2020-3-92-101.
#
1. Page E.S. Continuous Inspection Schemes. Biometrika. 1954;41;1:100—115.
2. Nikiforov I.V. Posledovatel'noe Obnaruzheniya Izmeneniya Svojstv Vremennyh Ryadov. M.: Nauka, 1983. (in Russian).
3. Shafid A. Bibliometric Analysis of EWMA and CUSUM Control Chart Schemes. ITEE J. 2018;7;2: 1—11.
4. Shiryaev A.N. Zadacha Skorejshego Obnaruzheniya Narusheniya Stacionarnogo Rezhima. Doklady AN SCSR. 1961;138;5:1039—1042. (in Russian).
5. Crosier R.B. Multivariate Generalizations of Cumulative Sum Quality-control Schemes. Technometrics. 1988;30:291—303.
6. Chan L.K., Zhang J. Sharts Cumulative Sum Control for the Covariance Matrix. Statistica Sinica. 2001; 11:767—790.
7. Ngai H.M., Zhang J. Multivariate Cumulative Sum Control Charts Based on Projection Pursuit. Statistica Sinica. 2001;11:747—766.
8. Runger, G.C., Testik M.C. Multivariate Extensions to Cumulative Sum Control Charts. Quality and Reliability Eng. Intern. 2004;20:587—606.
9. Yeh A.B., Lin D.K., McGrath R.N. Multivariate Control Chart for Monitoring Covariance Matrix: a Review. Quality Techn. & Quantitative Management. 2006;3: 415—436.
10. Liu L., Zhong J., Ma Y. A Multivariate Synthetic Control Chart for Monitoring Covariance Matrix Based on Conditional Entropyю Proc. 19th Intern. Conf. Industrial Eng. and Eng. Management. Berlin: Springer, 2013: 99—107.
11. Filaretov G.F., Chervova A.A. Posledovatel'nyj Algoritm Obnaruzheniya Momenta Izmeneniya Dispersii Vremennogo Ryada. Zavodskaya Laboratoriya. Diagnostika Materialov. 2019;85;3:75—82. (in Russian).
12. Levin B.R. Teoreticheskie Osnovy Statisticheskoj Radiotekhniki. M.: Sovetskoe Radio, 1975. (in Russian).
13. Ayvazyan S.A., Mhitaryan V.S. Prikladnaya Statistika i Osnovy Ekonometriki. M.: YUNITI, 1998. (in Russian).
---
For citation: Filaretov G.F., Simonenkov P.S. A Cumulative Sum Algorithm for Detecting Changes in the Covariance Matrix of Multidimensional Time Series. Bulletin of MPEI. 2020;3:92—101. (in Russian). DOI: 10.24160/1993-6982-2020-3-92-101.
