Detection Capability of the Modified EWMA Chart for the Trend Stationary AR(1) Model

  • Piyatida Phanthuna Department of Applied Statistics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand
  • Yupaporn Areepong Department of Applied Statistics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand
  • Saowanit Sukparungsee Department of Applied Statistics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand
Keywords: Average run length (ARL), exponential white noise, autoregressive model, explicit formula

Abstract

A performance of control chart is frequently evaluated by using the average run length (ARL) which is calculated with several methods. Regarding this research paper, an explicit formula is a presented technique for computing the ARL of the modified EWMA chart with the trend AR(1) model in the scope of exponential white noise. The numerical integral equation (NIE) method is compared to the performance with the explicit formula. Accordingly, the results show that the explicit formula can find the solutions correctly and quickly. Moreover, the modified EWMA chart is used to compare a capability with the EWMA scheme. As a result, the performance of the modified EWMA control chart is better for small and moderated shifts. In addition, this explicit formula of the ARL is applied by using the real data of a health field.

Downloads

Download data is not yet available.
Published
2020-12-28
Section
Articles