Control Charts When the Observations Are Correlated.
Abstract
Traditionally, quality control charts have been designed with respect to statistical criteria only, and the control methodology is based on the independence and normality of serial samples. At first the production process is assumed to be characterized by a single in-control state. For example, if the process has one measurable quality characteristic, then the in-control state will correspond to the mean of this quality characteristic when no assignable cause is present. Keywords: Autoregressive models; Time series; Multivariate analysis.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 1987
- Accession Number
- ADA186388
Entities
People
- B. Q. Miao
- Paruchuri R. Krishnaiah
Organizations
- University of Pittsburgh