The effect of measurement error on calculated change point based on MLE

Control charts are one of the most well-known statistical process control tools used for quick detecting changes in the process. During this control process, we observe distinct points, which are spotted out of the control limits. However, it is known that these time spots are not ones that the process starts to get out of control (A drastic change in its parameters). For the reason of economy, efficiency and waste control, experts are to detect these starting points; called change points. Change points analysis is a powerful new tool for determining whether a change has taken. It is capable of detecting subtle changes missed by control charts. One of the methods for detecting change point is Maximum Likelihood Estimation (MLE). One of the challenges of analyzing quality control charts is measurement error in sampling. The presence of measurement error in quality control charts reduces their performance and delays quick reaction to changes. It also affects on determining the change point. In this paper, providing to prove the influence of measurement error in delaying the calculated amount of change point, which is derived by using MLE method is aimed.

Keywords:

Change point , measurement error , MLE , ̅ charts