Strong Consistency of Estimators for Heteroscedastic Partly Linear Regression Model under Dependent Samples

[摘要] In this paper we are concerned with the heteroscedastic regression modelyi=xiβ+g(ti)+σiei, 1≤i≤nunder correlated errorsei, where it is assumed thatσi2=f(ui), the design points(xi,ti,ui)are known and nonrandom, andgandfare unknown functions. The interest lies in the slope parameterβ. Assuming the unobserved disturbanceeiare negatively associated, we study the issue of strong consistency for two different slope estimators: the least squares estimator and the weighted least squares estimator.

[学科分类] 应用数学