非正态条件下过程能力指数的统计推断.pdf

浙江工商大学硕士论文是小样本,其实际覆盖率也和名义覆盖率相差较小。这说明广义置信区间估计方法在非正态条件下的过程能力指数统计推断中有较好的效果,希望为其在实际生产过程中的应用奠定理论基础。关键词:非正态分布;过程能力指数;广义置信区间;广义枢轴量: 覆盖率万方数据浙江工商大学硕士论文 STATISTICAL INFERENCE OFNON-NORM睑L PROCESS CPABILITY INDICES ABSTRACT Process capability refers totheuniformity also means theability of aprocess toproduce output within specification limits which considered international standards,national standards, industry standards and customer capability indices O'Os)is astatisticalmeasure ofprocess ’S also allimportant indicator inquality concept of PCIs only holds meaning forprocesses that ale in are usually calculated by thespecification limitsratioprocess fluctuation. The standard PCIs calculations require thequa:ity characteristics should follow anormal ,the distribution oftheunderlying quality characteristics datais withthedepartures from the normality assumption could lead to erroneous results when applying conventional statisticalcapability measures tonon-normal distributions. Sincenon-normally distributed processes are not mon inpractice, process capability fornon-normal datahas been widely studied inquality management. 万方数据浙江工商大学硕士论文 Inthispaper,we use theapproach proposed byClements(1989)to handle non—normal data,focusing on thestudy instatisticalinference of corresponding mon non—normal distributions as examples isWeibull distribution,Lognormal distribution and Generalized Exponential goal is to explore the frequency property of generalized confidence interval applying the method whichWeerahandi(1993)put forward ,we construct generalized pivotal quantity(GPQ)for the parameters andprocess using simulation method different confidence level,choose differentsample sizeandget thecoverage of generalized confidence ,we find the frequency property ofgenerali