Online Program Home
My Program

Abstract Details

Activity Number: 670 - Advances in Statistical Process Control
Type: Contributed
Date/Time: Thursday, August 2, 2018 : 10:30 AM to 12:20 PM
Sponsor: Quality and Productivity Section
Abstract #328672 Presentation
Title: Xbar Chart with Estimated Parameters: New Formulas to Guarantee a Conditional In-Control Performance
Author(s): Felipe Jardim* and Subhabrata Chakraborti and Eugenio Kahn Epprecht
Companies: Pontifical Catholic University of Rio De Janeiro and University of Alabama and Pontifical Catholic University of Rio de Janeiro
Keywords: Xbar Control Chart Performance; Conditional Performance; Exceedance Probability Criterion; Control Limits Adjustments; Guaranteed In-Control Performance; Average Run Length
Abstract:

Recently, to design control charts with estimated parameters, a new perspective has emerged where the usual chart performance measure, the average run length (ARL), is recognized as a random variable that depends on the parameter estimates. In this context, a recent idea is to measure the chart performance with the probability of the ARL be greater than a specified value. This is called the exceedance probability criterion (EPC). In recent years, bootstrap method and approximate formulas were proposed to adjust the Xbar chart under normality to guarantee an in-control performance in terms of the EPC. These methods provide accurate, but not exact, results. Given this, in this paper, we present a summary of two recent papers written by us, under review, where we propose the use of an equation in which exact adjustments can be quickly calculated with a software such as RStudios. Furthermore, realizing the complexity of all these methods for a regular user, in these papers, we also derive a new simpler approximate formula which depends only on the well-known chi-square distribution. We show that this new simpler formula provides accurate results compared to the already existing ones.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program