一种新的广义对数正态分布点估计方法  

A new point estimation method of generalized log-normal distribution

作　　者：温录亮[1] 陈平炎[2] WEN Luliang;CHEN Pingyan(Foshan University,Foshan 528225,China;Jinan University,Guangzhou 510632,China)

机构地区：[1]佛山科学技术学院,广东佛山528225 [2]暨南大学,广州510632

出　　处：《重庆理工大学学报（自然科学）》2022年第8期290-296,共7页Journal of Chongqing University of Technology：Natural Science

基　　金：国家自然科学基金项目(12171203);广东省哲学社会科学“十三五”规划项目(GD20XYJ19)。

摘　　要：针对广义对数正态分布的参数估计问题,首次提出了广义对数正态分布形状参数一种新的强相合的点估计量,并给出推导证明过程。利用逆变换抽样方法对点估计量进行数值模拟,将点估计和极大似然估计、贝叶斯估计结果进行对比,结果表明这种点估计方法在进行相关大数据分布模型参数估计时,具有较好的应用价值。In order to estimate the parameters of generalized lognormal distribution, a new strongly consistent point estimator for shape parameters of generalized lognormal distribution is proposed for the first time, and the derivation and proof process is given. The inverse transformation sampling method is used to simulate the point estimator, and the result of the point estimation is compared with the maximum likelihood estimation and Bayesian estimation. It is concluded that the point estimation method has a good application value in the parameter estimation of the relevant big data distribution model.

关 键 词：广义对数正态分布 点估计 逆变换抽样 大样本 数值模拟 

分 类 号：O212.1[理学—概率论与数理统计]