固定设计下半参数回归模型中的随机加权逼近  

Random Weighted Approximation in Semiparametric Regression Model Under Fixed Design

作　　者：薛留根[1] 田萍[1] 

机构地区：[1]北京工业大学应用数理学院,北京100022

出　　处：《北京工业大学学报》2004年第2期247-251,共5页Journal of Beijing University of Technology

基　　金：北京市自然科学基金资助项目(1042002).

摘　　要：为了模拟参数估计的误差分布,研究了固定设计下半参数回归模型中参数估计的误差分布的随机加权逼近问题,构造了参数估计的随机加权统计量,在适当的条件下,证明了用随机加权统计量的分布去逼近原估计量的误差分布的精度可达到o(n-1/2).To simulate the error distribution of parametric estimation, the random weighted approximation of the error distribution of parametric estimation in the semiparametric regression model under fixed design is studied and the random weighted statistic is structured by means of random weighted method. Under proper conditions the distribution of the random weighted statistic is used to approximate the error distribution of the preestimation, the accuracy of which can reach o (n -1/2).

关 键 词：半参数回归模型 随机加权逼近 参数估计 

分 类 号：O212.7[理学—概率论与数理统计]