Metrics
7 Record Views
Journal article
The Effects of Autocorrelation and Outliers on Two-Sided Tolerance Limits
Journal of quality technology, Vol.31(3), pp.286-300
07/01/1999
Web of Science ID: WOS:000081344000003
Abstract
Tolerance limits are limits that include a specific proportion of the population at a given confidence level. They are used to make sure that the production will not be outside specifications. Tolerance limits are either designed based on the normality assumption, or established nonparametrically. In either case, no provision is made in the available design tables of tolerance limits for autocorrelated processes. In this article, we show how positive autocorrelation affects the confidence level of tolerance limits for a specified level of coverage of the population. We conclude that the effect of autocorrelation is negligible for standard tolerance limits (–0.4 ≤ p < 0.25). We give suggestions on how to use existing design tables for tolerance limits that assume normality and independence when in fact the process of interest is a first-order autoregressive process. We also address the effect of occasional outliers on the coverage of tolerance limits.
Related links
Details
- Title
- The Effects of Autocorrelation and Outliers on Two-Sided Tolerance Limits
- Publication Details
- Journal of quality technology, Vol.31(3), pp.286-300
- Resource Type
- Journal article
- Publisher
- Taylor & Francis
- Copyright
- © Taylor & Francis
- Identifiers
- WOS:000081344000003; 99380553394306600
- Academic Unit
- Hal Marcus College of Science and Engineering ; Mathematics and Statistics
- Language
- English