Statistical Inference of Partially Specified Spatial Autoregressive Model  

作　　者：Yuan-qing ZHANG Guang-ren YANG 

机构地区：[1]School of Finance and Business, Shanghai Normal University [2]School of Statistics & Management, Shanghai University of Finance & Economics [3]Key Laboratory of Mathematical Economics (SUFE) Ministry of Education [4]Department of Statistics, School of Economics, Jinan University

出　　处：《Acta Mathematicae Applicatae Sinica》2015年第1期1-16,共16页应用数学学报（英文版）

基　　金：Supported by the National Natural Science Foundation of China(Grant No.71371118,71471117,11101442,11471086);Foundation for Distinguished Young Talents in Higher Education of Guangdong(Grant No.LYM09011);Program for Changjiang Scholars and Innovative Research Team in University(PCSIRTIRT13077);the State Key Program of National Natural Science of China(Grant No.71331006);the Graduate Innovation Fund Project of Shanghai University of Finance and Economics(Grant No.CXJJ-2011-444)

摘　　要：This paper studies estimation of a partially specified spatial autoregressive model with heteroskedas- ticity error term. Under the assumption of exogenous regressors and exogenous spatial weighting matrix, the unknown parameter is estimated by applying the instrumental variable estimation. Under certain sufficient conditions, the proposed estimator for the finite dimensional parameters is shown to be root-n consistent and asymptotically normally distributed; The proposed estimator for the unknown function is shown to be consis- tent and asymptotically distributed as well, though at a rate slower than root-n. Consistent estimators for the asymptotic variance-covariance matrices of both estimators are provided. Monte Carlo simulations suggest that the proposed procedure has some practical value.This paper studies estimation of a partially specified spatial autoregressive model with heteroskedas- ticity error term. Under the assumption of exogenous regressors and exogenous spatial weighting matrix, the unknown parameter is estimated by applying the instrumental variable estimation. Under certain sufficient conditions, the proposed estimator for the finite dimensional parameters is shown to be root-n consistent and asymptotically normally distributed; The proposed estimator for the unknown function is shown to be consis- tent and asymptotically distributed as well, though at a rate slower than root-n. Consistent estimators for the asymptotic variance-covariance matrices of both estimators are provided. Monte Carlo simulations suggest that the proposed procedure has some practical value.

关 键 词：SPATIAL instrument variable SIEVE 

分 类 号：O212.1[理学—概率论与数理统计] O242.2[理学—数学]