A New Scheme for Monitoring Multivariate Process Dispersion

Title of dissertation: A New Scheme for Monitoring Multivariate Process Dispersion Xin Song, Doctor of Philosophy, 2009 Dissertation directed by: Professor Paul J. Smith Department of Mathematics Construction of control charts for multivariate process dispersion is not as straightforward as for the process mean. Because of the complexity of out of control scenarios, a general method is not available. In this dissertation, we consider the problem of monitoring multivariate dispersion from two perspectives. First, we derive asymptotic approximations to the power of Nagao’s test for the equality of a normal dispersion matrix to a given constant matrix under local and fixed alternatives. Second, we propose various unequally weighted sum of squares estimators for the dispersion matrix, particularly with exponential weights. The new estimators give more weights to more recent observations and are not exactly Wishart distributed. Satterthwaite’s method is used to approximate the distribution of the new estimators. By combining these two techniques based on exponentially weighted sums of squares and Nagao’s test, we are able to propose a new control scheme MTNT, which is easy to implement. The control limits are easily calculated since they only depend on the dimension of the process and the desired in control average run length. Our simulations show that compared with schemes based on the likelihood ratio test and the sample generalized variance, MTNT has the shortest out of control average run length for a variety of out of control scenarios, particularly when process variances increase. A New Scheme for Monitoring Multvariate Process Dispersion

[1]  Arthur B. Yeh,et al.  A multivariate exponentially weighted moving average control chart for monitoring process variability , 2003 .

[2]  James M. Lucas,et al.  Exponentially weighted moving average control schemes: Properties and enhancements , 1990 .

[3]  S. S. Wilks.  The Large-Sample Distribution of the Likelihood Ratio for Testing Composite Hypotheses , 1938 .

[4]  A decomposition for a stochastic matrix with an application to MANOVA , 2005 .

[5]  H. Nagao,et al.  Monotonicity of the modified likelihood ratio test for a covariance matrix , 1967 .

[6]  K. W. Kemp,et al.  Formal Expressions Which Can be Applied to Cusum Charts , 1971 .

[7]  Chien-Wei Wu,et al.  A multivariate EWMA control chart for monitoring process variability with individual observations , 2005 .

[8]  Charles W. Champ,et al.  A multivariate exponentially weighted moving average control chart , 1992 .

[9]  E. S. Page.  CONTINUOUS INSPECTION SCHEMES , 1954 .

[10]  S. W. Roberts.  Control chart tests based on geometric moving averages , 2000 .

[11]  B. V. Rao,et al.  Uniqueness and convergence of solutions to average run length integral equations for cumulative sum and other control charts , 2001 .

[12]  F. Aparisi,et al.  GENERALIZED VARIANCE CHART DESIGN WITH ADAPTIVE SAMPLE SIZES. THE BIVARIATE CASE , 2001 .

[13]  H. Nagao,et al.  On Some Test Criteria for Covariance Matrix , 1973 .

[14]  F. E. Satterthwaite.  An approximate distribution of estimates of variance components. , 1946, Biometrics.

[15]  N. Sugiura,et al.  Asymptotic non-null distributions of the likelihood ratio criteria for covariance matrix under local alternatives , 1973 .

[16]  D. Hawkins.  Multivariate quality control based on regression-adjusted variables , 1991 .

[17]  H. Nagao,et al.  Asymptotic expansions of some test criteria for homogeneity of variances and covariance matrices from normal populations , 1970 .

[18]  Sven Knoth,et al.  Accurate ARL computation for EWMA-S2 control charts , 2005, Stat. Comput..

[19]  Chi Song Wong,et al.  Wishart distributions associated with matrix quadratic forms , 2003 .

[20]  Gyo-Young Cho,et al.  Multivariate Control Charts for Monitoring the Mean Vector and Covariance Matrix , 2006 .

[21]  A. R. Crathorne,et al.  Economic Control of Quality of Manufactured Product. , 1933 .

[22]  Hans-Jürgen Reinhardt.  Analysis of Approximation Methods for Differential and Integral Equations , 1985 .

[23]  D. G. Nel,et al.  A Test to Determine Closeness of Multivariate Satterthwaite's Approximation , 1994 .

[24]  Yasunori Fujikoshi,et al.  Asymptotic Expansions of the Non-Null Distributions of the Likelihood Ratio Criteria for Multivariate Linear Hypothesis and Independence , 1969 .

[25]  Thomas Mathew,et al.  Wishart and Chi-Square Distributions Associated with Matrix Quadratic Forms , 1997 .

[26]  J. Macgregor,et al.  The exponentially weighted moving variance , 1993 .

[27]  J. Stuart Hunter,et al.  The exponentially weighted moving average , 1986 .

[28]  P. Robinson,et al.  Average Run Lengths of Geometric Moving Average Charts by Numerical Methods , 1978 .

[29]  A. Khuri.  A measure to evaluate the closeness of Satterthwaite's approximation , 1995 .

[30]  W. Jiang,et al.  AVERAGE RUN LENGTH COMPUTATION OF ARMA CHARTS FOR STATIONARY PROCESSES , 2001 .

[31]  Nathan Srebro,et al.  Learning with matrix factorizations , 2004 .

[32]  Charles W. Champ,et al.  A a comparison of the markov chain and the integral equation approaches for evaluating the run length distribution of quality control charts , 1991 .

[33]  George C. Runger,et al.  A Markov Chain Model for the Multivariate Exponentially Weighted Moving Averages Control Chart , 1996 .

[34]  Chi Song Wong,et al.  Multivariate versions of Cochran theorems , 1999 .

[35]  Maria E. Calzada,et al.  Reconciling the Integral Equation and Markov Chain Approaches for Computing EWMA Average Run Lengths , 2003 .

[36]  Tonghui Wang,et al.  Multivariate versions of Cochran's theorems II , 1993 .

[37]  G D Williamson,et al.  A study of the average run length characteristics of the National Notifiable Diseases Surveillance System. , 1999, Statistics in medicine.

[38]  Douglas C. Montgomery,et al.  Some Statistical Process Control Methods for Autocorrelated Data , 1991 .

[39]  N. Sugiura,et al.  Asymptotic Expansions of the Distributions of the Likelihood Ratio Criteria for Covariance Matrix , 1969 .

[40]  Nariaki Sugiura,et al.  Unbiasedness of Some Test Criteria for the Equality of One or Two Covariance Matrices , 1968 .

[41]  W. Y. Tan,et al.  On approximating a linear combination of central wishart matrices with positive coefficients , 1983 .

[42]  H. J. Huang,et al.  A synthetic control chart for monitoring process dispersion with sample standard deviation , 2005, Comput. Ind. Eng..

[43]  D. A. Evans,et al.  An approach to the probability distribution of cusum run length , 1972 .

[44]  J. Stoer,et al.  Introduction to Numerical Analysis , 2002 .

[45]  G. Runger,et al.  Multivariate control charts for process dispersion , 2004 .

[46]  Frank B. Alt.  Multivariate Quality Control , 1984 .

[47]  Shing I. Chang,et al.  Statistical Process Control for Variance Shift Detections of Multivariate Autocorrelated Processes , 2007 .

[48]  Frank B. Alt,et al.  17 Multivariate process control , 1988 .

[49]  Sven Knoth,et al.  The Art of Evaluating Monitoring Schemes — How to Measure the Performance of Control Charts? , 2006 .

[50]  S. Gupta,et al.  PROPERTIES OF POWER FUNCTIONS OF SOME TESTS CONCERNING DISPERSION MATRICES OF MULTIVARIATE NORMAL DISTRIBUTIONS , 1969 .

[51]  S. Crowder.  A simple method for studying run-length distribution of exponentially weighted moving average charts , 1987 .

[52]  J. Hull.  Options, Futures, and Other Derivatives , 1989 .

[53]  Peter Kritzer,et al.  Lattice-Nyström method for Fredholm integral equations of the second kind with convolution type kernels , 2007, J. Complex..