| 非线性再生散度随机效应模型的极大似然估计及EM算法 |
| |
| 引用本文： | 张文专,王学仁.非线性再生散度随机效应模型的极大似然估计及EM算法[J].生物数学学报,2009,24(2):355-362. |
| |
| 作者姓名： | 张文专 王学仁 |
| |
| 作者单位： | 张文专(贵州财经学院,数学与统计学院,贵州,贵阳,550004;贵州省经济系统仿真重点实验室,贵州,贵阳,550004);王学仁(云南大学,应用统计研究中心,云南,昆明,650091) |
| |
| 基金项目： | 国家自然科学基金资助项目，贵州省科学技术基金 |
| |
| 摘 要： | 非线性再生散度随机效应模型是指数族非线性随机效应模型和非线性再生散度模型的推广和发展．通过视模型中的随机效应为假想的缺失数据和应用Metropolis-Hastings（MH）算法，提出了模型参数极大似然估计的Monte-Carlo EM（MCEM）算法，并用模拟研究和实例分析说明了该算法的可行性．
|
| 关 键 词： | 非线性再生散度随机效应模型 极大似然估计 MCEM算法 MH算法 Newton Raphson迭代 |
Maximum Likelihood Estimation in Nonlinear Reproductive Dispersion Mixed Models and EM Algorithm |
| |
| Institution: | ZHANG Wen-Zhuan, WANG Xue-Ren (1 School of Mathematics and Statistics, Guizhou College of Finance and Economics, Guiyang Guizhou 550004 China;2 Guizhou Key Laboratory of Economic System Simulation, Guiyang Guizhou 550004 China;3 Research Center of Applied Statistics, Yunnan University, Kunming Yunnan 650091 China) |
| |
| Abstract: | Nonlinear reproductive dispersion models are natural extensions of exponential family nonlinear mixed models and Nonlinear reproductive dispersion models. After treating the random effects in the models as hypothetical missing data, this paper proposes an EM algorithm with Markov chain Monte-Carlo method for maximum likelihood estimation in the models. The proposed procedure is illustrated by a simulation study and a real example. |
| |
| Keywords: | MCEM algorithm Maximum likelihood estimation Metropolis-Hastings algorithm Newton-Raphson iteration Nonlinear reproductive dispersion mixed models |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
