Abstract
Traditional control charts are designed for processes were outputs are independent and identically distributed (i.i.d), and large amount of historical data set are available before the start of a production run. In many manufacturing environments there is neither enough observations nor the data are i.i.d. In this paper we propose the unknown parameters change point formulation in conjunction with residuals of various time series models as a statistical process control alternative for short run autocorrelated data. Based on the average run length and standard deviation of the run length as criteria of control chart’s performance, the proposed alternative is compared to other short run SPC techniques. Simulation results show that the change point model formulation provides better shift detection properties than residual charts based on the Q statistics.
Additional information
Notes on contributors
Abdelmonem Snoussi
Lecturer of statistics at the Higher Institute of Finance and Fiscal Studies, University of Sousse, Tunisia. His research interests include statistical quality control and statistical inference with applications. He is a member of Tunisian Management Science Society.
Mohamed Limam
Professor of Statistics at the University of Tunis, ISG, Tunisia. His research interests include applied statistics, quality control, experimental design, data mining and bioinformatics. His publications appeared in Journal of American Statistical Association, Communications in Statistics, Machine learning, Inter. Jour. of Production Research, Quality Technology and Quantitative Management and International Journal of Quality and Reliability Management. His is a member of ASQ, and of Tunisian Management Science Society.