A Statistical Control Chart for Monitoring High-dimensional Poisson Data Streams

A Statistical Control Chart for Monitoring High-dimensional Poisson Data Streams

0.00 Avg rating0 Votes
Article ID: iaor2017105
Volume: 33
Issue: 2
Start Page Number: 307
End Page Number: 321
Publication Date: Mar 2017
Journal: Quality and Reliability Engineering International
Authors: , ,
Keywords: production, service, quality & reliability, control, simulation
Abstract:

Multivariate count data are popular in the quality monitoring of manufacturing and service industries. However, seldom effort has been paid on high‐dimensional Poisson data and two‐sided mean shift situation. In this article, a hybrid control chart for independent multivariate Poisson data is proposed. The new chart was constructed based on the test of goodness of fit, and the monitoring procedure of the chart was shown. The performance of the proposed chart was evaluated using Monte Carlo simulation. Numerical experiments show that the new chart is very powerful and sensitive at detecting both positive and negative mean shifts. Meanwhile, it is more robust than other existing multiple Poisson charts for both independent and correlated variables. Besides, a new standardization method for Poisson data was developed in this article. A real example was also shown to illustrate the detailed steps of the new chart.

Reviews

Required fields are marked *. Your email address will not be published.