| 非线性半参数模型的虚拟观测法 |
| |
| 引用本文： | 王志忠,郭兴翠,周玉娜.非线性半参数模型的虚拟观测法[J].数学理论与应用,2007,27(2):60-63. |
| |
| 作者姓名： | 王志忠 郭兴翠 周玉娜 |
| |
| 作者单位： | 中南大学数学科学与计算技术学院 长沙410075 |
| |
| 摘 要： | 本文首先介绍非线性半参数回归中常用的补偿最小二乘法,然后基于先验信息将其转化成对此问题的虚拟观测,用虚拟观测与原观测联合,按常规的最小二乘方法求解.最后运用的实例计算结果表明,虚拟观测方法计算的结果一般优于常规的补偿最小二乘结果,基本上可达到理论上的最优解.
|
| 关 键 词： | 半参数模型 补偿最小二乘原理 虚拟观测 |
| 修稿时间： | 2006-12-06 |
Quasi Observation Approach of Nonlinear Semi--parametric Model |
| |
| Wang Zhizhong, Guo Xingcui, Zhou Yuna.Quasi Observation Approach of Nonlinear Semi--parametric Model[J].Mathematical Theory and Applications,2007,27(2):60-63. |
| |
| Authors: | Wang Zhizhong Guo Xingcui Zhou Yuna |
| |
| Institution: | School of Mathematical and Computing Techonology, Central South University, Changsha, 410075 |
| |
| Abstract: | In this paper the method of penalized least square(PLS) of nonlinear semi-parametric model is introduced at first.And then,the solution of the model is studied on the view of the prior information.It is suggested that the prior information on the semi-parameters is transformed into quasi observations,and the quasi observations are adjusted then together with the real observations.According to the simulating tests the quasi observation approach usually will be better than PLS.And it can get nearly the best theoretical result of PLS. |
| |
| Keywords: | Semi-parametric model Penalized least squares techniques Quasi observation |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
