| 缺失数据下含几何分布的对数线性模型的EM算法 |
| |
| 引用本文： | 王继霞,刘次华.缺失数据下含几何分布的对数线性模型的EM算法[J].应用数学,2009,22(2). |
| |
| 作者姓名： | 王继霞 刘次华 |
| |
| 作者单位： | 1. 河南师范大学数学与信息科学学院,河南,新乡,453007
2. 华中科技大学数学与统计学院,湖北,武汉,430074 |
| |
| 摘 要： | 本文研究缺失数据下对数线性模型参数的极大似然估计问题.通过Monte-Carlo EM算法去拟合所提出的模型.其中,在期望步中利用Metropolis-Hastings算法产生一个缺失数据的样本,在最大化步中利用Newton-Raphson迭代使似然函数最大化.最后,利用观测数据的Fisher信息得到参数极大似然估计的渐近方差和标准误差.
|
| 关 键 词： | 条件期望 极大似然估计 EM算法 Metropolis-Hastings算法 Newton-Raphson迭代 |
The EM Algorithm in Logistic Linear Models with Geometric Distribution Involving Missing Data |
| |
| WANG Ji-xia,LIU Ci-hua.The EM Algorithm in Logistic Linear Models with Geometric Distribution Involving Missing Data[J].Mathematica Applicata,2009,22(2). |
| |
| Authors: | WANG Ji-xia LIU Ci-hua |
| |
| Abstract: | In this paper,a geometric response and normal covariace model for the missing data are assumed.We fit the model using the Monte Carlo EM(Expectation and Maximization) algorithm.The E-step is derived by Metropolis-Hastings algorithm to generate a sample for missing data,and the M-Step is done by Newton-Raphson to maximize the likelihood function.Asymptotic variances and the standard errors of the MLE of parameters are derived using the observed Fisher information. |
| |
| Keywords: | Conditional expectation Maximum likelihood estimation EM algorithm Metropolis-Hastings algorithm Newton-Raphson iteration |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
