František Rublík

# Abstract:

Consistent estimators of the asymptotic covariance matrix of vectors of $U$-statistics are used in constructing asymptotic confidence regions for vectors of Kendall's correlation coefficients corresponding to various pairs of components of a random vector. The regions are products of intervals computed by means of a critical value from multivariate normal distribution. The regularity of the asymptotic covariance matrix of the vector of Kendall's sample coefficients is proved in the case of sampling from continuous multivariate distribution under mild conditions. The results are applied also to confidence intervals for the coefficient of agreement. The coverage and length of the obtained (multivariate) product of intervals are illustrated by simulation.

# Keywords:

U-statistics, vector of Kendall's coefficients, coefficient of agreement, confidence interval, consistent estimate of asymptotic covariance matrix

62G05, 62G15

# References:

1. B. Abdous, C. Genest and B. Rémillard: Dependence properties of meta-elliptical distributions. In: Statistical Modelling and Analysis for Complex Data Problems (P. Duchesne and B. Rémillard,eds.), Springer, New York, 2005, pp. 1-15.   DOI:10.1007/0-387-24555-3_1
2. A. S. C. Ehrenberg: On sampling from a population of rankers. Biometrika 39 (1952), 82-87.   DOI:10.1093/biomet/39.1-2.82
3. C. Genest, J. Nešlehová and N. Ben Ghorbal: Estimators based on Kendall's tau in multivariate copula models. Austral. and New Zealand J. Statist. 53 (2011), 157-177.   DOI:10.1111/j.1467-842x.2011.00622.x
4. L. A. Goodman: A simple simultaneous test procedure for quasi-independence in contingency tables. J. Royal Statist. Soc., Ser. C 20 2(1971), 165-177.   DOI:10.2307/2346464
5. J. Hájek, Z. Šidák and P. K. Sen: Theory of Rank Tests. Academic Press, San Diego 1999.   CrossRef
6. W. Hoeffding: A class of statistics with asymptotically normal distribution. The Annals Math. Statist. 19 (1948), 293-325.   DOI:10.1214/aoms/1177730196
7. H. Hult and F. Lindskog: Multivariate extremes, aggregation and dependence in elliptical distributions. Adv. Appl. Probab. 34 (2002), 587-608.   DOI:10.1239/aap/1033662167
8. M. G. Kendall and B. Babington Smith: On the method of paired comparisons. Biometrika 31 (1940), 324-345.   DOI:10.1093/biomet/31.3-4.324
9. J. F. C. Kingman and S. J. Taylor: Introduction to Measure and Probability. Cambridge University Press, Cambridge 1966.   DOI:10.1017/cbo9780511897214
10. A. J. Lee: U-Statistics: Theory and Practice. Marcel Dekker, Inc., New York 1990.   CrossRef
11. A. Liu, Q. Li, C. Liu, K. Yu and K. F. Yu: A rank-based test for comparison of multidimensional outcomes JASA 105 (2010), 578-587.   DOI:10.1198/jasa.2010.ap09114
12. H. El Maache and Y. Lepage: Spearman's rho and Kendalls's tau for multivariate data sets. In: Lecture Notes - Monograph Series 42, Mathematical Statistics and Applications, Festschrift for Constance van Eeden, Beachwood 2003, pp. 113-130.   CrossRef
13. C. R. Rao: Linear Statistical Inference and its Applications. John Wiley and Sons, New York 1973.   DOI:10.1002/9780470316436
14. P. K. Sen: On some convergence of U-statistics. Cal. Statist. Assoc. Bull. 10 (1960), 1-18.   CrossRef