摘要
给定来自一未知连续分布函数F的容量为n的子样x1,x2,…,xn,考虑分布函数F的不变估计问题.在非对称损失函数L(F(t),d(t))=b∫(exp{a[d(t)-F(t)]}-a[d(t)-F(t)]-1)dF(t)和单调变换群下得到F的最优不变估计为d(t,X)=∑ni=0ciI(x(i)≤t≤x(i+1)),其中ci=1/aln(∫01ti(1-t)n-idt)/(∫01exp{-at}ti(1-t)n-idt),a≠0,b>0.
Given a random sample ofx1,x2,…,xnsize n from an unknown continuous distributionfunction F, this paper considers the problem of invariant estimator of the continuous distributionfunction F. Under the unsymmetrical loss function Z,(F(t),d(t))=b∫(exp{a[d(t)-F(t)]}-a[d(t)-F(t)]-1)dF(t), we get the best invariant estimator of the continuous distribution function F.
出处
《广西科学》
CAS
2007年第4期365-366,共2页
Guangxi Sciences
关键词
非对称损失
连续分布函数
不变估计
unsymmetrical loss,continuous distribution function,invariant estimator