1. Title: “AN APPLICATION OF ENSEMBLE TREES IN MULTIVARIATE STATISTICAL PROCESS CONTROL (MSPC)”
2. Objectives: The most widely used tools in statistical quality control are control charts. However, the main problem of multivariate control charts, including the Hotelling‘s T ² control chart, lies in that they indicate that a change in the process has happened, but do not show which variable or variables are the source of this shift. Although a number of methods have been proposed in the literature for tackling this problem, the most usual approach consists in decomposing the T ² statistic.
In this paper, we propose an alternative method interpreting this task as a classification problem and solving it through the application of boosting with classification trees. The classifier is then used to determine which variable or variables caused the change in the process.
3. Data/Methods: This paper uses simulated data to analyze whether classification trees are a good alternative to determine which variable or variables are the source of the change in the process.
4. Results/Expected results: The results prove this method to be a powerful tool for interpreting multivariate control charts.
5. Conclusion: The main contribution of this research paper is to propose the use of boosting trees using the SAMME algorithm to interpret the out-of-control signals that occur in multivariate process quality control. These ensemble trees have proved to be a very powerful tool when classifier accuracy is a key factor. It is worth mentioning that our proposal is a combined two-step approach: we first detect the out-of-control signal using well-known Hotelling’s T ² control chart, and we then apply the boosting classifier to determine which variable or variables have changed.
Key words: Statistical quality control, boosting trees.