非线性E-V回归模型中参数估计的渐近性质

ASYMPTOTIC BEHAVIOR OF PARAMETRIC ESTIMATION IN NONLINEAR E-V REGRESSION MODELS

本文讨论了非线性E-V回归模型中参数的估计问题,构造了未知参数β0的最小二乘估计β和误差方差σ2的估计σ2,证明了β具有渐近正态性,同时也证明了σ2依概率收敛于σ2的速度可达到n-1/2.

This paper considers the problem of the parametric estimation in nonlinear error-invariable regression models. The estimator β of unknown parametric β0 and the estimator σ2 of error variance σ2 are structured respectively. The author proves that under suitable conditions the estimator β is asymptotically normality and the rate that σ2 in probability converge to σ2 can attain the accuracy of n-1/2.