Article ID: | iaor20051728 |
Country: | United Kingdom |
Volume: | 21 |
Issue: | 1 |
Start Page Number: | 51 |
End Page Number: | 61 |
Publication Date: | Jan 2005 |
Journal: | Quality and Reliability Engineering International |
Authors: | Tang Loon-Ching, Gao Yinfeng |
Keywords: | markov processes, statistics: sampling |
The Dodge chain sampling plan (ChSP-1) and its extensions are very useful in situations where testing is either destructive or costly. Its underlying assumption is that all units to be inspected are from the same process and the quality characteristic of interest follows an identical independent distribution. Although this assumption makes the model relatively simple and easy to implement, it may not hold for today's manufacturing processes with high production volume, in which correlation exists between products within the same process. In this paper, we propose a Markov chain model for chain sampling plans to model the dependency (correlation) between testing units. To achieve this, we assume that product units within each sample follow a Markov chain model and assume that they are independent when they are from different lots. The resulting OC curves and AOQ curves show that the discriminating power of chain sampling plans improves when there is a negative correlation between product units and deteriorates when the correlation is positive.