摘要
过程能力指数(C_p)估计的关键是对总体标准差的估计。在多个子样本情形下,采用4个无偏估计量■,■_s,■_R,■_p分别估计总体标准差σ,证明了直接以此为基础的过程能力指数的估计量都是有偏的,且都有高估C_p的倾向;之后构造了C_p的4个无偏估计量;探讨了其中3个无偏估计量的估计效率;最后结合案例计算了C_p的不同估计值。
The key point to estimate the process capability indices （i.e., Cp） is the estimator of the population standard deviation, which can be represented by the following unbiased estimator：σ,σs,σRand σp It is verify that all the estimators of Cp based directly on σ,σs,σRand σp are biased. Furthermore, they tend to overestimated the true value of Cp. Then, four unbiased estimators are put forward, and the efficiency of three of them is explored as well. Finally, each estimation method is analyzed in an example.
出处
《数理统计与管理》
CSSCI
北大核心
2010年第6期1009-1017,共9页
Journal of Applied Statistics and Management
关键词
多个子样本
过程能力指数
估计量
总体标准差
multi-subgroups, process capability indices, estimator, standard deviation of population
