逆瑞利分布和对数逻辑分布下过程能力指数的区间估计

Interval estimation for the process capability index under the inverse Rayleigh and log-logistic distributions

讨论在逆瑞利分布和对数逻辑分布下一个重要的过程能力指数C Npk的统计推断问题。构造C Npk的广义枢轴量,然后提出其广义置信区间。数值结果表明,所提出的区间估计在覆盖率和区间长度方面比bootstrap方法具有更好的性能。

The process capability indices are widely applied to measure the productivity of a process in manufacturing and industrial applications.In this paper,we discuss the statistical inferential problem on an important process capability index C Npk under the inverse Rayleigh and log-logistic distributions.We construct the generalized pivotal quantities for C Npk,and subsequently the generalized confidence intervals proposed.Numerical results show that the proposed interval estimation performs better than the bootstrap method in terms of coverage rate and interval width.