Proceedings of the Korean Statistical Society Conference (한국통계학회:학술대회논문집)
- 2003.10a
- /
- Pages.97-103
- /
- 2003
Optimal Designs for Attribute Control Charts
Abstract
Shewhart-type control charts have historically been used for attribute data, though they have ARL biased property and even are unable to detect the improvement of a process with some process parameters. So far most efforts have been made to improve the performance of attribute control charts in terms of faster detection of special causes without increasing the rates of false alarm. In this paper, control limits are proposed that yield an ARL (nearly) unbiased chart for attributes. Optimal design is also proposed for attribute control charts under a natural sense of criterion.