函数型线性回归模型的三角样条估计  

Triangular spline estimation for the functional linear model

作　　者：张恒 朱永忠[1] 

机构地区：[1]河海大学理学院,江苏南京211100

出　　处：《云南民族大学学报（自然科学版）》2017年第6期475-477,共3页Journal of Yunnan Minzu University:Natural Sciences Edition

基　　金：国家自然科学基金(5079029)

摘　　要：函数型数据的回归分析研究主要集中在函数型线性回归模型,基于三角样条估计的方法对模型中未知参数进行了估计.通过仿真实验验证了三角样条估计的均方误差比传统的多项式样条估计的均方误差更小,且在计算上用时更少,由此得出三角样条估计在部分函数型线性回归模型中具有一定的优越性.The functional linear regression model has captured much attention in functional data analysis. In this paper,the unknown parameters in the model are estimated based on the triangular spline estimation method. The simulation results show that the mean square error of the triangular spline estimation is smaller than that of the traditional polynomial spline estimation and the triangular estimation spends less time in calculation. It is concluded that the triangular spline estimation has some advantages in the partial functional linear regression model.

关 键 词：函数型线性回归模型 函数型数据 三角样条 均方误差 

分 类 号：O174.4[理学—数学]