拟似然非线性模型的统计诊断  

A Statistical Diagnosis for Quasi-Likelihood Nonlinear Models

作　　者：宋蕾 冯予[1] SONG Lei;FENG Yu(School of Science,Nanjing University of Science and Technology,Nanjing 210094,China)

机构地区：[1]南京理工大学理学院,江苏南京210094

出　　处：《湖南工业大学学报》2019年第1期54-59,共6页Journal of Hunan University of Technology

基　　金：国家自然科学基金资助项目(11271189)

摘　　要：研究了经验似然估计下的拟似然非线性模型的统计诊断问题。首先给出了模型经验似然比函数,进而求出模型的经验似然估计;再基于数据删除模型推导出参数的一阶近似公式,并提出了经验Cook距离;最后通过对实例的分析,验证了该统计方法的有效性和合理性。A research has been conducted on the statistical diagnosis of quasi-likelihood nonlinear models based on empirical likelihood estimation.Firstly,the empirical likelihood ratio function of the model has been provided,thus obtaining the empirical likelihood estimation of the model.Then,based on the case deletion model,the first-order approximation formula of parameters is to be derived,with the empirical Cook distance subsequently proposed.Finally,the validity and rationality of the statistical method can be verified by an analysis of a case study.

关 键 词：拟似然非线性模型 经验似然 数据删除模型 经验Cook距离 强影响点 

分 类 号：O212[理学—概率论与数理统计]