极值分布的极大似然估计及计算机实现  

Maximum Likelihood Estimation of the Parameters of the Extreme Value Distribution and Computer Implementation

作　　者：尚英姿[1] 安润秋[2] 

机构地区：[1]西安交通大学管理学院 [2]唐山学院基础部,河北唐山063000

出　　处：《河北师范大学学报（自然科学版）》2006年第6期643-646,共4页Journal of Hebei Normal University：Natural Science

基　　金：国家自然科学基金资助项目(70473071)

摘　　要：极值分布在计量经济学、金融工程、计算生物学、工程测量中都有用途,一般常用最小二乘法估计其参数,但最小二乘法的误差较高.极大似然估计具有比最小二乘法更好的性质,但由于它的计算往往比较麻烦.通过极大似然法估计了极值分布的参数,同时给出了求参数的数值解的算法,并通过Matlab程序实现了这一算法.Extreme value large set of independent, ident There are lots of application ment. Usually people use least higher error. Instead, by using value distributions parameters distributions are often used to model the smallest or largest value among a ically distributed random values representing measurements or observations. in quantitative economics, finance, bioinformaties and engineering measuresquares to estimate the parameters. Unfortunately, least squares method has maximum likelihood estimation,a numerical method to estimate the extreme is developed and this algorithm in Matlab is implemented.

关 键 词：极值分布 极大似然估计 算法 

分 类 号：O212.1[理学—概率论与数理统计]