【摘要】 本文探讨了随机删失场合半参数回归模型的参数估计问题．考虑半参数回归模型Y=X’β+g（T）+e其中（X，T）为取值于RP×[0，1]上的随机向量，β为p维未知参数向量，g为定义于[0，1]上的未知函数，e为随机误差，Ee=0，Ee2=σ2＞0未知，且（X，T）与e独立，Y被一个与之独立的随机变量V所截．此时仅能观察到：Z=min（Y，V），δ=I（Y≤V），参数β，σ2的估计量βn及σn2可综合非参数的权函数估计法与参数的最小二乘估计方法得到．本文对核函数的情形得到了βn及σn2的精确收敛速度即重对数律．更多还原

【Abstract】 This paper studied the parameter estimation in a semiparametric regression model with censored data. A semiparametric regression modelY = X’β+g (T) +ewas taken into account,where (X,T) is a random vector onm Rp×[0, 1],β is a p-dimensional unknown parameter, g (·) is an unknown function on [0, 1],e is a random error with mean 0 and variance σ2, (X,T) is independent of e. And Y may be censored and therefore not completely observable,where the censoring variable V and the variable Y are independent mutually. We estimate β and σ2 by nonparametric weight function and least square method. As a result,this paper prove that these estimations β; and σn 2of βand σ2 have the law of iterated logarithm.更多还原