CONTEXT-TREE APPROACH FOR MONITORING THE MULTI-WAY CONTINGENCY TABLES-BASED PROCESSES WITH DEPENDENCE BETWEEN NEIGHBORHOOD CELLS

Authors

  • Reza Kamranrad Department of Industrial Engineering, Faculty of Engineering, Semnan University, Semnan, Iran
  • Azadeh Golshan Department of Industrial Engineering, University of Science and Culture, Tehran, Iran
  • Farnoosh Bgheri Department of Quantitative Systems, University Canada West, Vancouver, BC, Canada

DOI:

https://doi.org/10.23055/ijietap.2024.31.2.8171

Abstract

In recent years, some statistical process monitoring (SPM) approaches have been used to control contingency table-based processes. The common assumption in this research is that the Neighborhood cells of the contingency table are temporally independent. This paper develops a new approach based on the Context-Tree method and Kullback-Leibler (KL) statistic to monitor the multi-way contingency tables by considering the dependence between Neighborhood cells in Phase II. The proposed approach is evaluated by using some simulation studies. In addition, the efficiency of the proposed approach has been approved using other sensitivity analyses in some numerical examples by contingency tables with more rows and columns and contingency tables with more categorical variables. Results show that proposed statistics have suitable performance in detecting the out-of-control condition under different shifts in a multi-way contingency table.

Published

2024-04-18

How to Cite

Kamranrad, R., Golshan, A., & Bgheri, F. (2024). CONTEXT-TREE APPROACH FOR MONITORING THE MULTI-WAY CONTINGENCY TABLES-BASED PROCESSES WITH DEPENDENCE BETWEEN NEIGHBORHOOD CELLS . International Journal of Industrial Engineering: Theory, Applications and Practice, 31(2). https://doi.org/10.23055/ijietap.2024.31.2.8171

Issue

Section

Quality, Reliability, Maintenance Engineering