| 系数随机的多元线性回归模型的参数估计 |
| |
| 引用本文： | 王磊. 系数随机的多元线性回归模型的参数估计[J]. 应用基础与工程科学学报, 1994, 0(Z1) |
| |
| 作者姓名： | 王磊 |
| |
| 作者单位： | 中国水稻研究所 浙江杭州 |
| |
| 摘 要： | 对一般系数随机的带有相关因子的多元线性回归模型的参数进行估计。估计值是用EM算法给出的极大似然估计或约束的极大似然估计。给出了EM算法的具体公式,并利用bootstrap方法估算出这些估计值的精确度。最后通过一判别儿童总体中是否存在Catch-Up生长的例子以解释给出的方法。
|
| 关 键 词： | 随机系数 EM算法 bootstrap方法 极大似然估计 约束的极大似然估计 Catch-Up生长 |
ESTIMATION OF PARAMETERS IN RANDOM COEFFICIENT MULTIVARIATE LINEAR REGRESSION MODELS |
| |
| Lei WANGChina National Rice Research Institute,Hangzhou. ESTIMATION OF PARAMETERS IN RANDOM COEFFICIENT MULTIVARIATE LINEAR REGRESSION MODELS[J]. Journal of Basic Science and Engineering, 1994, 0(Z1) |
| |
| Authors: | Lei WANGChina National Rice Research Institute Hangzhou |
| |
| Affiliation: | Lei WANGChina National Rice Research Institute,Hangzhou 310006 |
| |
| Abstract: | EM algorithm is employed to find maximum likelihood estimates or restricted maximum likelihood estimates for parameters in the general multivariate linear regression models while incorporating related covariates. Detailed EM algorithm is derived, while the accuracy of these estimates can be approximated by using bootstrap method. One example from the growth studies is used to illustrate the method. The results answer the question of whether or not catch-up growth is present in the population. |
| |
| Keywords: | random coefficients EM algorthm bootstrap method maximum likelihood estimation restricted maximum likelihood estimation catch-up growth |
| 本文献已被 CNKI 等数据库收录！ |
