Kendall correlation coefficient for order statistics
摘要
In the present paper, we study the relationship between the order statistics by using the Kendall correlation coefficient. We show that this relationship is positive and decreases as the distance between indices of order statistics increases for a fixed sample size. We also compare the values of the Kendall correlation coefficient for order statistics with the corresponding values of the Pearson correlation coefficient. We conduct simulation experiments, and these experiments sustain our theoretical results and show that the Kendall correlation coefficient of order statistics has better precision than the Pearson correlation coefficient.