变系数部分函数型二元选择模型的统计推断  

Statistical inference for partial functional varying coefficient binary choice model

作　　者：王龙兵 张忠占[2] WANG Long-bing;ZHANG Zhong-zhan(College of Teacher Education,Quzhou University,Quzhou 324000,China;Faculty of Science,Beijing University of Technology,Beijing 100124,China)

机构地区：[1]衢州学院教师教育学院,浙江衢州324000 [2]北京工业大学理学部,北京100124

出　　处：《高校应用数学学报（A辑）》2024年第4期413-425,共13页Applied Mathematics A Journal of Chinese Universities(Ser.A)

基　　金：国家自然科学基金(12271014);衢州学院博士科研启动项目(BSYJ202117)。

摘　　要：基于B样条sieve方法,该文研究变系数部分函数型二元选择模型的估计及其渐近性质.在一定的条件下,证明了变系数函数的估计与斜率函数的估计的强相合性和渐近正态性.在一定的条件下,变系数函数的估计与斜率函数的估计达到最优收敛速度.数值模拟和Tecator data的实证分析表明文中提出的估计方法是可行有效的.In this paper,based on the Bspline sieve method,the estimation and asymptotic properties of the partial functional varying coefficient binary choice model are studied.Under certain conditions,the strong consistency and asymptotic normality of the estimates of varying coefficient functions and slope function are proved.Under certain conditions,the estimation of the varying coefficient function and the estimation of the slope function achieve the optimal convergence rate.Numerical simulation and empirical analysis of Tecator data show that the proposed estimation method is feasible and effective.

关 键 词：变系数回归模型 函数型数据 二元选择模型 B样条 渐近性质 

分 类 号：O212[理学—概率论与数理统计]