均匀分布顺序统计量的相关性  

Correlation of Order Statistics for Uniform Distribution

作　　者：丁勇 Ding Yong(School of Science,Kangda College of Nanjing Medical University,Lianyungang Jiangsu 222000,China)

机构地区：[1]南京医科大学康达学院理学部,江苏连云港222000

出　　处：《统计与决策》2022年第15期29-33,共5页Statistics & Decision

摘　　要：文章推导了均匀分布顺序统计量相关系数和偏相关系数的计算公式。结果表明,顺序统计量之间为正相关,相关系数的大小与均匀分布的取值区间无关,最小顺序统计量和最大顺序统计量有最小的相关系数,相关系数矩阵有许多独特的性质。偏相关系数非负且小于相关系数,最小顺序统计量和最大顺序统计量的偏相关系数为零;消除位于两个顺序统计量之间的任意一个顺序统计量的影响后,这两个顺序统计量的偏相关系数为零。This paper derives the calculation formulas of correlation coefficient and partial correlation coefficient for uniform distribution order statistics. The results are shown as below: There is a positive correlation between the order statistics;the size of the correlation coefficient is independent of the value interval of the uniform distribution;the minimum order statistics and the maximum order statistics have the minimum correlation coefficient;the correlation coefficient matrix has many unique properties.The partial correlation coefficient is not negative and smaller than the correlation coefficient;the partial correlation coefficient of the minimum order statistics and the maximum order statistics is zero. When is eliminated the effect of either order statistic that lies between two order statistics, the partial correlation coefficient of the two order statistics is zero.

关 键 词：均匀分布 顺序统计量 相关系数 偏相关系数 

分 类 号：O212.1[理学—概率论与数理统计]