Confidence Intervals for a Discrimination Ratio in a Gauge R&R Study with Three Random Factors
Authors:
- 1 April 2003
- journal article
- Published by Taylor & Francis in Quality Engineering
- Vol. 15 (3) , 383-389
Abstract
In this paper, we extend results of the typical two-factor gauge repeatability and reproducibility (R&R) study to a situation with three random factors. The objective of this study is to form a confidence interval on a discrimination ratio used to determine the adequacy of the measurement system. Two confidence intervals are proposed and evaluated for effectiveness with regard to confidence coefficient and interval length using computer simulation. The basic conclusions are that: i) a closed-form interval that is easily computable performs well in a variety of conditions, ii) a more intensive computational method performs slightly better than the closed-form interval, and iii) increased replications do not have much affect on interval length.Keywords
This publication has 9 references indexed in Scilit:
- Measurement System Assessment via Generalized InferenceJournal of Quality Technology, 2000
- Two-Way Random-Effects Analyses and Gauge R&R StudiesTechnometrics, 1999
- THE ECONOMIC EVIPACT OF MEASUREMENT ERRORQuality Engineering, 1999
- Confidence Intervals on Measures of Variability in R&R StudiesJournal of Quality Technology, 1997
- Confidence intervals on ratios of linear combinations for non-disjoint sets of expected mean squaresJournal of Statistical Planning and Inference, 1995
- Confidence Intervals on Variance Components1992
- Generalized p -Values in Significance Testing of Hypotheses in the Presence of Nuisance ParametersJournal of the American Statistical Association, 1989
- Confidence intervals on a ratio of variances in the two-factor nested components of variance modelCommunications in Statistics - Theory and Methods, 1981
- An Approximate Distribution of Estimates of Variance ComponentsBiometrics Bulletin, 1946