基于似然比检验的EWMA控制图  

Likelihood Ratio Test-based EWMA Control Chart

作　　者：李阳 LI Yang(School of Management,Xi'an Polytechnic University,Xi'an 710048,China)

机构地区：[1]西安工程大学管理学院

出　　处：《价值工程》2020年第3期195-196,共2页Value Engineering

摘　　要：似然比统计量是比较常用的检验统计量。其基本假设是数据服从正态分布,基于极大似然估计得到统计量的基本形式。其对正态分布下数据位置参数和尺度参数的监测效果较好,但对于非正态分布下的具体表现不得而知。在此将似然比统计量与EWMA结合,并比较分析似然比统计量在不同分布下检测位置参数和尺度参数的表现。The likelihood ratio statistic is the most common test statistic.The basic assumption is that the data is obtained from the normal distribution and the basic form of the statistic is obtained based on the maximum likelihood estimation(MLE).The monitoring effect of the data location parameters and scale parameters under normal distribution is good,but the concrete performance of the data under non-normal distribution is not known.In this paper,the likelihood ratio statistic is combined with EWMA,and the performances of the location parameters and the scale parameters of the likelihood ratio statistics under different distributions are compared and analyzed.

关 键 词：似然比统计量 统计过程控制 指数加权移动平均 

分 类 号：O212[理学—概率论与数理统计] O213.1[理学—数学]