摘要
借助于Copula这一工具对在具有联合分布H(x,y)的二维总体(X,Y)经概率积分变换得到的随机变量H(X,Y)的分布函数K(V)给定条件下,求出关于次序统计量X(n)=max{X1,X2,…,Xn}和Y(n)=max{Y1,Y2,…,Yn}经概率积分变换得到的随机变量Hn(X(n),Y(n))的分布函数Kn(v)的方法进行了研究,并找出了Kn(v)不随样本容量n变化的情形,进而得到了较准确地刻画二维R.V相依性的相关性指标Kendall'sτ.
Shows the approachs of finding the distribution function K_n(v) corresponding to the bivariate probability integral transformation(BIPIT) of pairs (X_((n)),Y_((n))) given the distribution function K(V) of random variable H(X,Y) obtained by taking the BIPIT of a random pair(X,Y)with distribution function (H(X,Y).where) X_((n))=max{X_1,X_2,…,X_n}and Y(n) max{Y_1,Y_2…,Y_n}, illustrate the conditions of invariability of (K_n(v)).Furthermore, obtained the Kentall's τ which can characterize the dependence orderings exactly.
出处
《河北大学学报（自然科学版）》
CAS
2004年第5期464-467,471,共5页
Journal of Hebei University(Natural Science Edition)
