多层线性模型参数估计的MCEM算法  

Application of MCEM Algorithm to the Parameter Estimation for Hierarchical Linear Models

作　　者：卢玉桂[1] 韦新星 赵丽棉[1] 

机构地区：[1]河池学院数学与统计学院,广西宜州546300

出　　处：《数学的实践与认识》2016年第11期225-230,共6页Mathematics in Practice and Theory

基　　金：河池学院硕士专业学位建设基金课题(2015YTB005);河池学院青年课题(XJ2015QN013);河池学院2015年度课堂教学模式改革项目(2015KTJY11)

摘　　要：应用Monte Carlo EM(MCEM)算法给出了多层线性模型参数估计的新方法,解决了EM算法用于模型时积分计算困难的问题,并通过数值模拟将方法的估计结果与EM算法的进行比较,验证了方法的有效性和可行性.Hierarchical linear model can be implemented via the EM algorithm.However,because of its difficulty in calculating the explicit expression of integral in E step,the application is Umited.This paper proposes a new algorithm,which is based on the MCEM algorithm,and to implement the two layers hierarchical linear models.Later its excellence in obtaining the estimate of hierarchical linear models is illustrated by a numerical example.

关 键 词：MCEM算法 多层线性模型 MONTE CARLO模拟 

分 类 号：O212.1[理学—概率论与数理统计]