双幂变换下参数极大似然估计的精确分布研究
A study of the accurate distribution of the maximum likelihood estimates for parameters under dual power transformation
云南民族大学学报:自然科学版,2016,25(3):246-250

丘甜 QT

摘要


在双幂变换下,使用极大似然估计方法估计正态线性回归模型中的变换参数,并研究其精确分布.给出了极大似然估计的精确分布函数,并通过模拟研究表明了,其分布不仅依赖于变换参数取值,还与方差和回归系数的取值密切相关;得到极大似然估计是一奇异随机变量, 不具有密度函数的结论.为双幂变换的应用提供了很重要的理论依据. Under dual power transformation, this paper uses the maximum likelihood estimation to estimate the parameters in the normal linear regression model and then studies their accurate distribution. It provides the accurate distribution function of the maximum likelihood estimates. And the simulation study shows that the distribution not only depends on the value of parameters but also is closely related to the value of variance and regression coefficients. It has reached the conclusion that the maximum likelihood estimate, which is a singular random variable, has no density function, which provides a very important theoretical basis for the use of dual power transformation.

参考



全文: PDF      下载: 887      浏览: 149


counter for myspace
云南民族大学学报(自然科学版) 1991—2016 Copyright
地址:云南省昆明市一二.一大街134号 邮编:650031 全国邮发代号:64-47
电话:0871-65132114 传真:0871-65137493 Email:ynmzxyxb@163.com