Maximum likelihood estimation of change point from stationary to nonstationary in autoregressive models using dynamic linear model
Reza Sheikhrabori
Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, Iran
Search for more papers by this authorCorresponding Author
Majid Aminnayeri
Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, Iran
Correspondence
Majid Aminnayeri, Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, 424 Hazfez Ave, Tehran, Iran, 15875-4413.
Email: [email protected]
Search for more papers by this authorMona Ayoubi
Department of Industrial Engineering, College of Engineering, West Tehran Branch, Islamic Azad University, Tehran, Iran
Search for more papers by this authorReza Sheikhrabori
Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, Iran
Search for more papers by this authorCorresponding Author
Majid Aminnayeri
Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, Iran
Correspondence
Majid Aminnayeri, Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, 424 Hazfez Ave, Tehran, Iran, 15875-4413.
Email: [email protected]
Search for more papers by this authorMona Ayoubi
Department of Industrial Engineering, College of Engineering, West Tehran Branch, Islamic Azad University, Tehran, Iran
Search for more papers by this authorAbstract
Change point estimation is a useful concept in time series models that could be applied in several fields such as financing, quality control. It helps to decrease costs of decision making and production by monitoring stock market and production lines, respectively. In this paper, the maximum likelihood technique is developed to estimate change point at which the stationary AR(1) model changes to a nonstationary process. Filtering and smoothing of dynamic linear model are used to estimate unknown parameters after change point. We also assume that correlation exists between samples' statistics. Simulation results show the effectiveness of the proposed estimators to estimate the change point of stationary. In addition based on Shewhart control chart, filtering has a better accuracy in comparison to smoothing. A real example is provided to illustrate the application.
REFERENCES
- 1Safaeipour A, Niaki STA. Drift change point estimation in multistage processes using MLE. Int J Reliabil Qual Safety Eng. 2015; 22(05):1550025.
- 2Page ES. Continuous inspection schemes. Biometrika. 1954; 41(1/2): 100-115.
- 3Nishina K. A comparison of control charts from the viewpoint of change-point estimation. Qual Reliabil Eng Int. 1992; 8(6): 537-541.
10.1002/qre.4680080605 Google Scholar
- 4Ayoubi M, Kazemzadeh RB, Noorossana R. Change point estimation in the mean of multivariate linear profiles with no change type assumption via dynamic linear model. Qual Reliabil Eng Int. 2016; 32(2): 403-433.
- 5Samuel TR, Pignatiello JJ Jr, Calvin JA. Identifying the time of a step change with X control charts. Qual Eng. 1998; 10(3): 521-527.
10.1080/08982119808919166 Google Scholar
- 6Samuel TR, Pignatiello JJ Jr, Calvin JA. Identifying the time of a step change in a normal process variance. Qual Eng. 1998; 10(3): 529-538.
10.1080/08982119808919167 Google Scholar
- 7Pignatiello JJ Jr, Samuel TR. Estimation of the change point of a normal process mean in SPC applications. J Qual Technol. 2001; 33(1): 82.
- 8Noorossana R, Saghaei A, Paynabar K, Abdi S. Identifying the period of a step change in high-yield processes. Qual Reliabil Eng Int. 2009; 25(7): 875-883.
- 9Perry MB, Pignatiello JJ Jr. Estimation of the change point of a normal process mean with a linear trend disturbance in SPC. Qual Technol Quant Mgt. 2006; 3(3): 325-334.
10.1080/16843703.2006.11673118 Google Scholar
- 10Perry MB, Pignatiello JJ, Simpson JR. Estimating the change point of a Poisson rate parameter with a linear trend disturbance. Qual Reliabil Eng Int. 2006; 22(4): 371-384.
- 11Perry MB, Pignatiello JJ, Simpson JR. Estimating the change point of the process fraction non-conforming with a monotonic change disturbance in spc. Qual Reliabil Eng Int. 2007; 23(3): 327-339.
- 12Noorossana R, Shadman A. Estimating the change point of a normal process mean with a monotonic change. Qual Reliabil Eng Int. 2009; 25(1): 79-90.
- 13Ghazanfari M, Alaeddini A, Niaki STA, Aryanezhad MB. A clustering approach to identify the time of a step change in Shewhart control charts. Qual Reliabil Eng Int. 2008; 24(7): 765-778.
- 14Alaeddini A, Ghazanfari M, Nayeri MA. A hybrid fuzzy-statistical clustering approach for estimating the time of changes in fixed and variable sampling control charts. Inform Sci. 2009; 179(11): 1769-1784.
- 15Ahmadzadeh F. Change point detection with multivariate control charts by artificial neural network. Int J Adv Mftng Technol. 2009; 1-12.
- 16Atashgar K, Noorossana R. An integrating approach to root cause analysis of a bivariate mean vector with a linear trend disturbance. Int J Adv Mftng Technol. 2011; 52(1): 407-420.
- 17Amiri A, Allahyari S. Change point estimation methods for control chart postsignal diagnostics: a literature review. Qual Reliabil Eng Int. 2012; 28(7): 673-685.
- 18Ayoubi M, Kazemzadeh R, Niaki S, Amiri A. Change Point Estimation of a Multivariate Normal Process Mean Using Dynamic Linear Model: Submitted; 2014.
- 19Ayoubi M, Kazemzadeh R, Noorossana R. Estimating multivariate linear profiles change point with a monotonic change in the mean of response variables. Int J Adv Mftng Technol. 2014; 75(9–12): 1537-1556.
- 20Kawahara Y, Sugiyama M. Sequential change-point detection based on direct density-ratio estimation. Statistic Anal Data Mining: The ASA Data Sci J. 2012; 5(2): 114-127.
10.1002/sam.10124 Google Scholar
- 21Choi H, Ombao H, Ray B. Sequential change-point detection methods for nonstationary time series. Dent Tech. 2008; 50(1): 40-52.
- 22Liu S, Yamada M, Collier N, Sugiyama M. Change-point detection in time-series data by relative density-ratio estimation. Neural Netw. 2013; 43: 72-83.
- 23Qiang S, Chanjian F, Wenlong L. The research on the new recognition method of non-stationary time series. IJACT: Int J Advance Comput Technol. 2013; 5(1): 149-157.
- 24Guralnik V, Srivastava J. Event detection from time series data. Paper presented at: Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining, 1999.
- 25Serinaldi F. Use and misuse of some Hurst parameter estimators applied to stationary and non-stationary financial time series. Physic A: Statistic Mechanics Appl. 2010; 389(14): 2770-2781.
10.1016/j.physa.2010.02.044 Google Scholar
- 26Hawkins DM, Zamba K. A change-point model for a shift in variance. J Qual Technol. 2005; 37(1): 21
- 27Ho S-S, Wechsler H. Detecting changes in unlabeled data streams using martingale. Paper presented at: IJCAI, 2007.
- 28Laurent H, Doncarli C. Stationarity index for abrupt changes detection in the time-frequency plane. IEEE Signal Process Letters. 1998; 5(2): 43-45.
- 29Knight MI, Nunes MA, Nason GP. Spectral estimation for locally stationary time series with missing observations. Stat Comput. 2012; 22(4): 877-895.
10.1007/s11222-011-9256-x Google Scholar
- 30Birr S, Volgushev S, Kley T, Dette H, Hallin M. Quantile spectral analysis for locally stationary time series. J R Stat Soc Series B Stat Methodology. 2017;
- 31Malela-Majika JC, Rapoo E. Distribution-free mixed cumulative sum-exponentially weighted moving average control charts for detecting mean shifts. Qual Reliabil Eng Int. 2017.
- 32Amiri A, Zolfaghari S. Estimation of change point in two-stage processes subject to step change and linear trend. Int J Reliabil Qual Safety Eng. 2016; 23(02):1650007.
- 33Chang ST, Lu KP. Change-point detection for shifts in control charts using EM change-point algorithms. Qual Reliabil Eng Int. 2016; 32(3): 889-900.
10.1002/qre.1800 Google Scholar
- 34Lu K-P, Chang S-T, Yang M-S. Change-point detection for shifts in control charts using fuzzy shift change-point algorithms. Comp Industr Eng. 2016; 93: 12-27.
10.1016/j.cie.2015.12.002 Google Scholar
- 35Montgomery DC. Introduction to Statistical Quality Control. New York: John Wiley & Sons; 2009.
- 36Petris G, Petrone S, Campagnoli P. Dynamic Linear Models With R. New York: Springer-Verlag; 2007.
- 37West M. STA 214: probability & statistical models2006. https://www2.stat.duke.edu/~km68/materials/214.2%20(AR1).pdf
