Consistency and asymptotic normality of profile-kernel and backfitting estimators in semiparametric reproductive dispersion nonlinear models
Semiparametric reproductive dispersion nonlinear model(SEDNM)is an extension of reproductive dispersion nonlinear model and semiparametric regression model，and includes semiparametric nonlinear model and semiparametric generalized linear model as its special case. Based on the local kernel estimator of nonparametric component，profile-kernel and backfitting estimators of parameters of interest are proposed in SRDNM，and theoretical comparison of both estimators is also investigated in this article. Under some regularity conditions，strong consistency and asymptotic normality of two estimators are shown.It is shown that the backfitting method produces a larger asymptotic variance than that for the profile-kernel method.
渐近常态 非线性模型 半参数回归模型 渐近正态性 内核参数 核估计
Nian-Sheng Tang Xue-Dong Chen Xue-Ren Wang
Department of Statistirs,Yunnan University,Kunming 650091, China
国内会议
北京
英文
108-123
2008-11-11（万方平台首次上网日期，不代表论文的发表时间）