| 带有缺失数据线性回归模型的变量选择 |
| |
| 引用本文： | 赵培信. 带有缺失数据线性回归模型的变量选择[J]. 河池师专学报, 2009, 0(2): 1-4 |
| |
| 作者姓名： | 赵培信 |
| |
| 作者单位： | [1]河池学院数学系,广西宜州546300; [2]北京工业大学应用数理学院,北京100124 |
| |
| 基金项目： | [基金项目]国家自然科学基金资助项目（10871013）;高等学校博士学科点专项科研基金资助项目（20070005003）. |
| |
| 摘 要： | 通过惩罚估计方程，对响应变量随机缺失下的线性回归模型，给出了一个变量选择方法，并结合局部二次逼近，得到了一个迭代算法，证明了此变量选择方法是相合的并且所得估计达到最优的参数收敛速度，最后通过数据模拟研究了此方法的有限样本性质．
|
| 关 键 词： | 变量选择 缺失数据 惩罚估计方程 |
Variable Selection for Linear Regression Models with Missing Data |
| |
| ZHAO Pei-xin. Variable Selection for Linear Regression Models with Missing Data[J]. Journal of Hechi Normal College, 2009, 0(2): 1-4 |
| |
| Authors: | ZHAO Pei-xin |
| |
| Affiliation: | ZHAO Pei-xin ( 1. Department of Mathematics, Hechi University, Yizhou, Guangxi 546300 ; 2. College of Applied Sciences, Beijing University of Technology, Beijing 100124, China) |
| |
| Abstract: | Based on penalized estimating equations, a variable selection procedure for linear regression models is proposed. By using local quadratic approximation, an iterative algorithm is also introduced. The optimal convergence rate and the consistency are derived. A simulation study is undertaken to assess the finite sample performance of the proposed method. |
| |
| Keywords: | variable selection missing data penalized estimating equations |
| 本文献已被 维普 等数据库收录！ |
