The restricted EM algorithm under inequality restrictions on the parameters
The restricted EM algorithm under inequality restrictions on the parameters
复制标题
参数不等式限制下的受限EM算法
DOI：
10.1016/s0047-259x(03)00134-9
复制
发表时间：
2005-01-01
影响因子：
1.6
通讯作者：
Guo, JH
中科院分区：
文献类型：
--
作者：
Shi, NZ;Zheng, SR;Guo, JH
EM算法是解决不完全数据问题的最有效的最大似然估计算法之一。在参数的线性限制下用于最大似然估计的限制EM算法已经由Kim和Taylor（J. Amer. Statist. 430（1995）708-716）。本文提出了不等式约束下极大似然估计的EM算法A（0 β）≥ 0，其中β是线性模型W = Xbeta + σ中的参数向量，σ是均值为零的正态分布误差变量，方差矩阵σ> 0是已知或未知的.讨论了ENT序列的一些收敛性质。此外，我们考虑了约束EM估计的相合性和一个相关的检验问题。(C)2003年爱思唯尔公司All rights reserved.
One of the most powerful algorithms for maximum likelihood estimation for many incomplete-data problems is the EM algorithm. The restricted EM algorithm for maximum likelihood estimation under linear restrictions on the parameters has been handled by Kim and Taylor (J. Amer. Statist. Assoc. 430 (1995) 708-716). This paper proposes an EM algorithm for maximum likelihood estimation under inequality restrictions A(0beta)greater than or equal to0, where beta is the parameter vector in a linear model W = Xbeta + epsilon and epsilon is an error variable distributed normally with mean zero and a known or unknown variance matrix Sigma > 0. Some convergence properties of the ENT sequence are discussed. Furthermore, we consider the consistency of the restricted EM estimator and a related testing problem. (C) 2003 Elsevier Inc. All rights reserved.