Abstract
A two-sided cumulative sum (CUSUM) chart may be defined as a joint plot of the successive values of a pair of upper and lower one-sided cumulative sum statistics. The standard procedure used to initialize these statistics consists in assigning a fixed starting value to each one of them. Each starting value may be taken equal to either zero or a fixed constant chosen to provide a fast initial response to the chart. In this article, the performance of a two-sided CUSUM chart is analyzed assuming that the pair of upper and lower one-sided statistics is initialized at a random point which follows a suitable defined joint stable distribution for the chart. This policy may be called the random intrinsic fast initial response (RIFIR) starting policy for the two-sided CUSUM chart. The article provides an algorithm to compute the stable distribution corresponding to the RIFIR starting policy as well as methods to evaluate the run-length distributions for in-control and out-of control situations. An important consequence of the stability of the RIFIR starting distribution is that, if no level shifts and no false alarms have occurred for a sufficiently large time interval (0, τ), the CUSUM chart behaves after τ as if the RIFIR initialization was used at τ, no matter how the chart was initialized at 0.
Similar content being viewed by others
References
Barnard, G. A. (1959). Control charts and stochastic processes.Journal of the Royal Statistical Society. Series B, 21:239–267.
Box, G. E. P. andLuceño, A. (1997).Statistical Control by Monitoring and Feedback Adjustment. John Wiley & Sons, New York.
Brook, D. andEvans, D. A. (1972). An approach to the probability distribution of CUSUM run length.Biometrika, 59:539–549.
Ewan, W. D. andKemp, K. W. (1960). Sampling inspection of continuous processes with no autocorrelation between successive results.Biometrika, 47:363–380.
Gan, F. F. (1993). The run length distribution of a cumulative sum control chart.Journal of Quality Technology, 25:205–215.
Goel, A. L. andWu, S. M. (1971). Determination of A. R. L. and a contour nomogram for CUSUM charts to control normal mean.Technometrics, 13:221–230.
Hawkins, D. M. andOlwell, D. H. (1998).Cumulative Sum Charts and Charting for Quality Improvement, Springer-Verlag, New York.
Horn, R. A. andJohnson, C. R. (1991).Matrix Analysis. Cambridge University Press, New York.
Kenett, R. S. andZacks, S. (1998).Modern Industrial Statistics. Duxbury Press, Pacific Grove.
Lucas, J. M. andCrosier, R. B. (1982). Fast initial response for CUSUM quality control schemes.Technometrics, 24:199–205.
Luceño, A. (1999a). Average run lengths and run length probability distributions for cuscore charts to control normal mean.Computational Statistics and Data Analysis, 32:177–195.
Luceño, A. (1999b). Discrete approximations to continuous univariate distributions-An alternative to simulation.Journal of the Royal Statistical Society. Series B, 61:345–352.
Luceño, A. andPuig-Pey, J. (2000). Evaluation of the run-length probability distribution for CUSUM charts: Assessing chart performance.Technometrics, 42:411–416.
Luceño, A. andPuig-Pey, J. (2002). Computing the run length probability distribution for CUSUM charts.Journal of Quality Technology, 34:209–215.
Luceño, A. andPuig-Pey, J. (2006). The random intrinsic fast initial response of one-sided CUSUM charts.Journal of Applied Statistics, 33:189–201.
Moustakides, G. V. (1986). Optimal stopping times for detecting changes in distributions.The Annals of Statistics, 14:1379–1387.
Page, E. S. (1954). Continuous inspection schemes.Biometrika, 41:100–115.
Page, E. S. (1961). Cumulative sum charts.Technometrics, 3:1–9.
Press, W. H., Teukolsky, S. A., Vetterling, W. T., andFlannery, B. P. (1992).Numerical Recipes. Cambridge University Press, New York, 2nd ed.
Stoer, J. andBulirsch, R. (1993).Introduction to Numerical Analysis. Springer-Verlag, New York, 2nd ed.
Woodall, W. H. (1983). The distribution of the run length of one-sided CUSUM procedures for continuous random variables.Technometrics, 25:295–301.
Woodall, W. H. (1984). On the Markov chain approach to the two-sided CUSUM procedure.Technometrics, 26:41–46.
Yashchin, E. (1985). On the analysis and design of CUSUM-Shewhart control schemes.IBM Journal of Research and Development, 29:377–391.
Author information
Authors and Affiliations
Corresponding author
Additional information
This research has been partially supported by the DGI Grant MTM2005-00287
Rights and permissions
About this article
Cite this article
Luceno, A., Cofiño, A.S. The random intrinsic fast initial response of two-sided CUSUM charts. Test 15, 505–524 (2006). https://doi.org/10.1007/BF02607064
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02607064