不等式约束条件下部分线性回归模型的参数估计

Estimation of Parameters for the Partial Linear Regression Models with Inequality Constraints

本文研究了不等式约束条件下部分线性回归模型的参数估计问题,利用最优化方法和贝叶斯方法,给出了不等式约束条件下部分线性回归模型的最小二乘核估计和最佳贝叶斯估计,并且证明了在一定条件下,带约束条件的最小二乘核估计在均方误差意义下要优于无约束条件的最小二乘核估计。

In this paper, we discuss the estimation of parameters for the partial linear regression models with inequality con- straints. With the methods of optimization and Bayesian, we give the least square kernel estimator and the best Bayesian esti- marion of the partial linear regression models with inequality constraints, and, we show that the least square kernel estimator with restriction condition is superior to the least square kernel estimator in terms of mean squsres error.