Numerical Approximation to the Performance of CUSUM Charts for EMA (1) Process

Authors: K. Petcharat, Y. Areepong, S. Sukparungsri, G. Mititelu

Abstract:

These paper, we approximate the average run length (ARL) for CUSUM chart when observation are an exponential first order moving average sequence (EMA1). We used Gauss-Legendre numerical scheme for integral equations (IE) method for approximate ARL0 and ARL1, where ARL in control and out of control, respectively. We compared the results from IE method and exact solution such that the two methods perform good agreement.

Keywords: Cumulative Sum Chart, Moving Average Observation, Average Run Length, Numerical Approximations.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1060653

References:

[1] E.S. Page, "Continuous Inspection Schemes," Biometrika, Vol. 41, No. 1, 1954, pp. 100-115.
[2] V.V. Mazalov, and D.N. Zhuravlev, "A Method of Cumulative Sums in the Problem of Detection of Traffic in Computer Networks," Program. Comput. Soft., Vol. 28 No.6, 2002, pp. 342-348.
[3] E.A. Bakhodir, "Sequential Detection of US Business Cycle Turning Points: Performances of Shiryayev-Roberts, CUSUM and EWMA Procedures," Econ. Papers, Submitted for publication.
[4] M. Ben, and J. Antony "Statistical Process Control an Essential Ingredient for Improving Service and Manufacturing Quality" Managing Service Quality, Vol.10, No.4, 2000, pp. 233-238.
[5] P.D. Kennedy, "Some Martingales Related to Cumulative Sum Test and Single-Server Queues Stoch. Proc. Appl., Vol. 4, 1975, pp. 261-269.
[6] T.O. Lim, A. Soraya, L.M. Ding, and Z. Morad, "Assessing Doctors' Competence: Application of CUSUM Technique in Monitoring Doctors' Performance," Int. J. Qual. Health C., Vol. 14, No.3, 2002, pp. 251-258.
[7] T. Sibanda, and N. Sibanda, "The CUSUM Chart method as a Tool for Monitoring of Clinical Outcomes Using Routinely Collected Data," BMC Medical Research Methodology, Vo.7, No. 46, 2007.
[8] L. Noyez, "Control Charts, CUSUM Techniques and Funnel Plots. A Review of Methods for Monitoring Performance in Healthcare," Interactive Cardio Vascular and Thoracic Surgery, Vol. 9, 2009, pp. 494-499.
[9] S. Vardeman, and D. Ray, "Average Run Lengths for CUSUM Schemes When Observations are Exponentially Distributed," Technometrics, Vol. 27, No. 2 ,May. 1985, pp. 145-150.
[10] S.V. Crowder, "A Simple Method for Studying Run Length Distributions of Exponentially Weighted Moving Average Charts," Technometrics, Vol.29. No. 4, Nov. 1987, pp.401-407
[11] M.S. Srivastava, and Y. Wu, "Evaluation of Optimum Weights and Average Run Lengths in EWMA Control Schemes," Commun. Stat. Theory., Vol. 26, 1997, pp. 1253-1267.
[12] D. Brook, and D.A. Evans, "An Approach to the Probability Distribution of CUSUM Run Length," Biometrika, Vol. 59, 1972, pp. 539-548.
[13] J.M. Lucas, and M.S. Saccucci, "Exponentially Weighted Moving Average Control Schemes: Properties and Enhancements," Technometrics, Vol. 32, No.1, Feb. 1990, pp. 1-29.
[14] Y. Areepong, "An Integral Equation Approach for Analysis of Control Charts," Ph.D.Thesis in Mathematical Sciences, Faculty of Science, University of Technology, Sydney, 2009.
[15] G. Mititelu, V.V. Mazalov, and A. Novikov, "On CUSUM Procedure for Hyperexponential Distribution," Stat. Probabil. Lett., Submitted for publication.
[16] G. Mititelu, Y. Areepong, S. Sukparungsee, and A. Novikov, "Explicit Analytical Solutions for the Average Run Length of CUSUM and EWMA Charts," East-West J. Math., Vol. 1, 2010, pp. 253-265.
[17] K. Petcharat, Y. Areepong, S. Sukparungsee, and G. Mititelu, "Fitting Weibull Distributions with Hyperexponential to Evaluate the Average Run Length for Cumulative Sum Chart," In Proc. 14th Conf. the ASMDA Int. Soc. Appl. Stoch. Models and Data Anal..
[18] K. Petcharat, Y. Areepong, S. Sukparungsee, and G. Mititelu, "Fitting Pareto Distributions with Hyperexponential to Evaluate the Average Run Length for Cumulative Sum Chart," Int. J. Pure Appl. Math., Vol.77 No.1, 2012, pp. 233-244.
[19] D.G. Wardell, H. Moskovitz, and R.D. Plante, "Control Charts in the Presence of Data Correlation," Management Science, Vol. 38, No. 8, Aug.1992, pp. 1084-1105.
[20] M. Yashchin, "Performance of CUSUM Control Schemes for Serially Correlated Observations," Technometrics, Vol. 35 No. 1, Feb. 1993, pp. 37-52.
[21] N.F. Zhang, "A Statistical Control Chart for Stationary Process Data. Technometrics, Vol. 40. No. 1, Feb. 1998, pp. 24-38.
[22] C.W. Lu, and M.R. Reynolds, "CUSUM Charts for Monitoring an Autocorrelated Process," J. Qual. Technol., Vol. 33, Jul. 2001, pp. 316- 334.
[23] O.O. Atienza, L.C. Tang, and B.W. Ang, "A CUSUM Scheme for SPC Procedures for Monitoring Autocorrelated Processes Autocorrelated Observations," J. Qual. Technol., Vol. 34 No. 2, Apr. 2002, pp. 187-199.
[24] P.A. Jacob, and P.A.W. Lewis, P, "A Mixed Autoregressive-Moving Average Exponential Sequence and Point Process (EARMA 1, 1)," Adv. Appl. Probab., Vol. 9, No. 1, Mar. 1977; pp. 87-104.
[25] J.A. Lawrance, and P.A.W. Lewis, "An Exponential Moving-Average Sequence and Point Process (EMA1)," J. Appl. Probab., Vol. 14 No. 1, Mar. 1977;pp. 98-113.
[26] I. Mohamed, and F. Hocine, "Bayesian Estimation of an AR(1) Process with Exponential White Noise," A Journal of Theoretical and Applied Statistics, Vol. 37, No. 5, 2010, pp. 365-372.
[27] K. Petcharat, Y. Areepong, S. Sukparungsee, and G. Mititelu, "Exact Solution for Average Run Length of CUSUM Charts for MA(1) Process" Chiang Mai J. Sci. submitted for publication.
[28] J. Busaba, S. Sukparungsee, Y. Areepong, and G. Mititelu, "Numerical Approximations of Average Run Length for AR(1) on Exponential CUSUM," In proc. Int. multiconference of engineers and computer scientists, March 7-10, Hong Kong(IMECS 2012).