分组数据下线性回归模型的参数估计  

Estimating regression coefficients in linear models based on grouped data

作　　者：郑明[1] 项阳[1] 

机构地区：[1]复旦大学统计学系,上海200433

出　　处：《高校应用数学学报（A辑）》2009年第2期183-193,共11页Applied Mathematics A Journal of Chinese Universities(Ser.A)

摘　　要：讨论了分组数据下线性回归模型参数的MLE的存在、唯一性.通过EM算法获得MLE的近似解.通过SEM算法获得MLE的渐近协方差阵.In this paper, the existence and uniqueness of the maximum likelihood estimator（MLE） of regression coefficients in linear regression models based on grouped data are discussed. The approximate solution of MLE is obtained by EM algorithm, and the asymptotic variance-covariance matrices for regression coefficients are obtained by SEM algorithm. Simulations show that the methods are available.

关 键 词：MLE 分组数据 EM算法 SEM算法. 

分 类 号：O212.3[理学—概率论与数理统计]