| 降秩正态线性模型参数的无偏估计 |
| |
| 引用本文： | 苑延华,宋作忠,严质彬.降秩正态线性模型参数的无偏估计[J].黑龙江科技学院学报,2009,19(2):150-153. |
| |
| 作者姓名： | 苑延华 宋作忠 严质彬 |
| |
| 作者单位： | 1. 黑龙江科技学院,数力系,哈尔滨,150027
2. 哈尔滨工业大学控制理论与制导技术研究中心,哈尔滨,150001 |
| |
| 基金项目： | 黑龙江省教育厅科学技术研究项目 |
| |
| 摘 要： | 降秩正态线性模型的参数是不可估的。针对这一情况,在可识别性约束条件下,证明了降秩正态线性模型正规方程系数矩阵的逆是原模型正规方程系数矩阵的一个广义逆,进而得出可估函数的最小二乘估计是最优无偏估计的结论。同时,推导了一般协方差分析模型的参数估计的公式,举例证明单协变量两向协方差分析的一般解算方法。
|
| 关 键 词： | 降秩线性模型 可识别性约束条件 广义逆矩阵 单协变量两向协方差分析 |
Unbiased estimation of Singular Normal Linear Model parameter |
| |
| YUAN Yanhua,SONG Zuozhong,YAN Zhibin.Unbiased estimation of Singular Normal Linear Model parameter[J].Journal of Heilongjiang Institute of Science and Technology,2009,19(2):150-153. |
| |
| Authors: | YUAN Yanhua SONG Zuozhong YAN Zhibin |
| |
| Institution: | 1.Department of Mathematics and Mechanics;Heilongjiang Institute of Science and Technology;Harbin 150027;China;2.Control Theory and Guidance Technology Research Center;Harbin Institute of Technology;Harbin 150001;China |
| |
| Abstract: | The parameter of Singular Normal Linear Model(SNLM) is not estimable.So,under the recognizable constraint condition,the inverse of coefficient matrix for the SNLM normal equation proves to be one generalized inverse of coefficient matrix for the normal equation of original model.Thus,it is concluded that the least squares estimation of estimable function is the best linear unbiased estimation.The formula of parameter estimation for the covariance analysis model is obtained.For a concrete case,the general so... |
| |
| Keywords: | Singular Normal Linear Model recognizable constraint condition generalized inverse matrix one-covariant and two-way categorical covariance analysis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
