An Empirical Bayes Attribute Control Chart for Process Fraction Defective.
Abstract
An empirical Bayes attribute control chart is developed for monitoring the fraction defective of a process (p-chart). The procedure requires no specific assumption regarding the incoming (prior) process distribution. Binomial sampling is assumed. The performance of the method is examined by means of extensive Monte Carlo simulation. Comparisons are made with the usual classical p-chart. In all cases the Empirical Bayes p-chart has larger power for detecting a shift in the mean of the process distribution. The procedure performs best when the process variation is small. The power is very large for detecting moderate shifts in the process mean. Finally, two real-data applications are presented, discussed, and appropriate conclusions drawn.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 31, 1975
- Accession Number
- ADA014621
Entities
People
- Harry F. Martz Jr.
- Prestone C. Chen
Organizations
- Texas Tech University