Efficient Statistical Inference for Partially Nonlinear Errors-in-Variables Models  

作　　者：San Ying FENG Gao Rong LI Jun Hua ZHANG 

机构地区：[1]College of Applied Sciences,Beijing University of Technology [2]College of Mechanical Engineering,Beijing Information Science and Technology University

出　　处：《Acta Mathematica Sinica,English Series》2014年第9期1606-1620,共15页数学学报（英文版）

基　　金：Supported by National Natural Science Foundation of China(Grant Nos.11101014 and 11002005);the Beijing Natural Science Foundation(Grant No.1142002);the Doctoral Fund of Innovation of Beijing Universityof Technology;the Science and Technology Project of Beijing Municipal Education Commission(Grant No.KM201410005010);the Training Programme Foundation for the Beijing Municipal Excellent Talents(GrantNo.2013D005007000005)

摘　　要：In this paper, we consider the partially nonlinear errors-in-variables models when the non- parametric component is measured with additive error. The profile nonlinear least squares estimator of unknown parameter and the estimator of nonparametric component are constructed, and their asymptotic properties are derived under general assumptions. Finite sample performances of the proposed statistical inference procedures are illustrated by Monte Carlo simulation studies.In this paper, we consider the partially nonlinear errors-in-variables models when the non- parametric component is measured with additive error. The profile nonlinear least squares estimator of unknown parameter and the estimator of nonparametric component are constructed, and their asymptotic properties are derived under general assumptions. Finite sample performances of the proposed statistical inference procedures are illustrated by Monte Carlo simulation studies.

关 键 词：Partially nonlinear errors-in-variables model measurement error ordinary smooth profile nonlinear least squares asymptotic property 

分 类 号：O212.1[理学—概率论与数理统计]