摘要
Ω为参数空间(p维欧氏空间的子集),X_i,i=1,…,n,为k维随机向量样本(iid.)取自未知分布F,p(x,t)为定义在R^k×Ω上的实函数(Ω为Ω之闭包),且假定p(x,t)≥C>-∞.具体的例子可见[1]与[2].关于M-估计量的统计性质,我们首先关心的θ_n是是否收敛,即当n→∞时。
This paper studies the asymptotic propertiesof M-estimators for the case where the parameter of interest is not uniquely defined.Under general situations,it is proved that the M-estima-tors are convergent in a sense weaker than the ordinary consistency.As an example,we discuss the convergence of the sample quantiles as estimators of the population quantiles.
出处
《应用数学学报》
CSCD
北大核心
1991年第4期533-538,共6页
Acta Mathematicae Applicatae Sinica
