J4

• 数学 • 上一篇    下一篇

部分线性回归模型中的广义似然比检验

施三支1,2, 宋立新3   

  1. 1. 吉林大学 数学学院, 长春 130012; 2. 长春理工大学 理学院, 长春 130022; 3. 大连理工大学 应用数学系, 辽宁省 大连 116024
  • 收稿日期:2006-04-04 修回日期:1900-01-01 出版日期:2007-01-26 发布日期:2007-01-26
  • 通讯作者: 宋立新

Generalized Likelihood Ratio Test in Partially Linear Models

SHI Sanzhi1,2, SONG Lixin3   

  1. 1. College of Mathematics, Jilin University, Changchun 130012, China; 2. School of Science, Changchun University of Science and Technology, Changchun 130022, China; 3. Department of Applied Mathematica, Dalian University of Technology, Dalian 116024, Liaoning Province, China
  • Received:2006-04-04 Revised:1900-01-01 Online:2007-01-26 Published:2007-01-26
  • Contact: SONG Lixin

摘要: 检验了部分线性回归模型中的函数部分是否为常数, 在备择假设下, 先用局部多项式方法估计出函数部分, 在估计中忽略了参数部分, 将其并入误差项, 再使用二阶段估计法, 直接应用最小二乘方法, 估计出参数部分, 并讨论了它们的渐近性质. 计算了零假设下广义似然比检验统计量的表达式, 并给出其渐近分布.

关键词: 部分线性回归模型, 局部多项式估计, 两阶段估计法, 广义似然比检验

Abstract: We proposed the test statistic to check whether the nonparametric function in partially linear models is a const or not. We estimated the nonparametric function by the local polynomial method, where we ignored the parametric component, and estimated the parameters by the two stage method. The test statistic under the null hypothesis was calculated, and it was shown to be a symptotically normal.

Key words: partially linear model, local polynomial estimation, two stage estimation, generalized likelihood ratio test

中图分类号: 

  • O212.1