Martingale approach to EWMA control charts for changes in exponential distribution
Exponentially weighted moving average (EWMA) procedure is a popular chart used for detecting small shifts of parameters of distributions in quality control and surveillance problems. The objective of this paper is to derive characteristics of a particular process such as Average Run Length (ARL)...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
Penerbit ukm
2008
|
| Online Access: | http://journalarticle.ukm.my/1867/ http://journalarticle.ukm.my/1867/ |
| Summary: | Exponentially weighted moving average (EWMA) procedure is a popular chart used for
detecting small shifts of parameters of distributions in quality control and surveillance
problems. The objective of this paper is to derive characteristics of a particular process such as
Average Run Length (ARL) and Average Delay time (AD) under EWMA procedure assuming
that observations follow an exponential distribution. Using the martingale approach we find
explicit expressions for characteristics of EWMA as Average Run Length (ARL) and
Average Delay time (AD). We compare the performance of the proposed expressions under
EWMA and other procedures such as CUSUM based ARL and AD using some simulation
studies |
|---|