Comparing Capability of Two Measurement Systems Based on Generalized Confidence Intervals

Abstract

Abstract: The method of comparing the capability of two measurement systems that measure the same quality characteristic in measurement system analysis is studied. Based on generalized inference, a method to compare two measurement systems capability is proposed. Through repeatability and reproducibility (R&R) studies, generalized confidence intervals for the comparison index of two measurement systems capability are built using generalized inference, and computer simulation is conducted. The results reveal that the proposed approach based on generalized confidence intervals can effectively compare capability of two measurement systems.

Key words: measurement system analysis, generalized confidence intervals, repeatability and reproducibility (R&R), analysis of variance (ANOVA)

Wu Xiao-fang，He Zhen，Shi Liang-xing. Comparing Capability of Two Measurement Systems Based on Generalized Confidence Intervals[J]. Industrial Engineering Journal , 2014, 17(5): 64-67.

References

［1］何桢,生静,施亮星. 测量系统的R&R分析在企业质量改进中的应用［J］. 工业工程, 2003, 6(1):62-66. He Zhen, Sheng Jing, Shi Liang-xing. Application of measurement system R&R analysis in quality improvement ［J］, Industrial Engineering, 2003, 6(1): 62-66. ［2］Burdick R K, Borror C M, Montgomery D C. A review of methods for measurement system capability analysis ［J］. Journal of Quality Technology, 2003, 35 (4): 342-354. ［3］吴小芳, 何桢, 施亮星. 基于向量的多元测量系统能力评价指数［J］. 系统工程, 2013, 31(3): 123-126. Wu Xiaofang, He Zhen, Shi Liang-xing. Multivariate Measurement System Capability Indices Based on Vector ［J］. System Engineering, 2013, 31(3): 123-126. ［4］Majeske K D. Twosample tests for comparing measurement systems ［J］. Quality Engineering, 2012, 24(4): 501-513. ［5］Burdick R K, Allen A E, Larsen G A. Comparing variability of two measurement process using R&R studies ［J］. Journal of Quality Technology, 2002, 34 (1): 97-105. ［6］Hamada M, Weerahandi S. Measurement system assessment via generalized inference ［J］. Journal of Quality Technology, 2000, 32 (3): 241-253. ［7］Burdick R K, Park Y J, Montgomery D C. Confidence intervals for misclassification rates in a gauge R&R study ［J］. Journal of Quality Technology, 2005, 37 (4): 294-303. ［8］Deldossi L, Zappa D. Measurement uncertainty with nested mixed effect method ［J］. Quality and Reliability Engineering International, 2011, 27(5): 673-679. ［9］Automotive Industry Action Group. Measurement systems analysis, 4th ed. ［M］. MI: Betroit, 2010. ［10］Woodall W H, Borror C M. Some relationships between gage R&R criteria ［J］. Quality and reliability engineering international, 2008, 24(1): 99106. ［11］Burdick R K, Borror C M, Montgomery D C, A review of methods for measurement systems capability analysis ［J］. Journal of Quality Technology, 2003, 35(4): 342–354. ［12］Tsui K, Weerahandi S. Generalized pvalues in significance testing of hypotheses in the presence of nuisance parameters ［J］. Journal of the American Statistical Association, 1989, 84(406): 602-607. ［13］Weerahandi S. Exact statistical methods for data analysis ［M］. New York: Springer, 1995. ［14］Chiang A K L. A simple general method for constructing confidence intervals for functions of variance components ［J］. Technometrics, 2001, 43 (3): 356-367. ［15］Mathew T, Webb D W. Generalized p values and confidence intervals for variance components: applications to army testing and evaluation ［J］. Technometrics, 2005, 47 (3): 312-322. ［16］Burdick R K, Larsen G A. Confidence intervals on measures of variability in R&R studies ［J］. Journal of Quality Technology, 1997, 29: 261-273.