.svg){kind=logo}
ON COMPARING THE ROBUSTNESS OF WEIGHTED AND UNWEIGHTED RANK CORRELATION COEFFICIENTS
Keywords:
weighted rank correlation, unweighted rank correlation, robustnessDOI:
https://doi.org/10.17654/0972361724042Abstract
Weighted rank correlation is needed in many cases where there are n objects ranked by two or more independent sources, and the interest is focused on situation when agreement in the top rankings is more important than bottom. In this paper, we aimed to compare between different weighted rank correlation coefficients with different unweighted rank correlation coefficients for different sample sizes in resisting outliers. The stability of Type I error is introduced through a simulation study applied on some bivariate distributions containing outliers. Within the weighted measures, we found that (Blest), (Salama-Quade 92) and (Costa-Soares) are most robust to resist outliers. Within the unweighted measures, the coefficients (Quadrant Association), (Fechner) and (Gideon-Hollister) are most robust to resist outliers. In general, we note that unweighted measures are more robust to resist outliers than the weighted measures based on the stability of Type I error.
Received: April 8, 2024
Revised: April 19, 2024
Accepted: April 23, 2024
References
D. C. Blest, Rank correlation - an alternative measure, Aust. N. Z. J. Stat. 42 (2000), 101-111.
N. Blomqvist, On a measure of dependence between two random variables, The Annals of Mathematical Statistics 21 (1950), 593-600.
G. E. P. Box and S. L. Anderson, Permutation in the derivation of robust criteria and the study of departures from assumptions, Journal of the Royal Statistical Society, Series B 17 (1955), 1-26.
J. P. Costa and C. Soares, A weighted rank measure of correlation, Aust. N. Z. J. Stat. 47 (2005), 515-529.
R. A. Gideon and A. Hollister, A rank correlation coefficient resistant to outliers, J. Amer. Statist. Assoc. 82 (1987), 656-666.
C. Gini, Il diverso accrescimento delle classi sociali e la concentrazione della ricchezza, Giornale degli Economisti 20 (1909), 27-83.
C. Genest and J.-F. Plante, Re: Pinto da Costa, J. & Soares, C. (2005). A weighted rank correlation problem, Aust. N. Z. J. Stat. 49 (2007), 203-204.
P. J. Huber, Robust statistics: a review, The Annals of Mathematical Statistics 43 (1972), 1041-1067.
M. G. Kendall, Rank Correlation Methods, 4th ed., Griffin, London, 1970.
A. Mano, Rank correlation coefficients: a new approach, computing science and statistics, computational statistics and data analysis on the Eve of the 21st century, Proceedings of the Second World Congress of the IASC, 29, 1997, pp. 471-476.
A. Mango, A distance function for ranked variables: a proposal for a new rank correlation coefficient, Metodološki zvezki 3 (2006), 9-19.
G. H. Moore and A. W. Wallis, Time series significance test based on sign differences, J. Amer. Statist. Assoc. 38 (1943), 153-165.
T. A. Maturi and E. H. Abdelfattah, A new weighted rank correlation, J. Math. Stat. 4 (2008), 226-230.
D. Quade and I. A. Salama, A survey of weighted rank correlation, P. K. Sen and I. A. Salama, eds., Order Statistics and Nonparametric: Theory and Applications, Elsevier Science Publishers B.V., Amsterdam, 1992, pp. 213-225.
I. A. Salama and D. Quade, A nonparametric comparison of two multiple regressions by means of a weighted measure of correlation, Comm. Statist. A-Theory Methods 11 (1982), 1185-1195.
I. A. Salama and D. Quade, The asymptotic normality of a rank correlation statistic based on rises, Statist. Probab. Lett. 32 (1997), 201-205.
T. Salvemini, Sui vari indici di concentrazione, Statistica 2 (1951), 133-154.
G. S. Shieh, A weighted Kendall’s tau statistic, Statist. Probab. Lett. 39 (1998), 17-24.
C. Spearman, The proof and measurement of association between two things, British Journal of Psychology 2 (1906), 89-108.
A. Tarsitano, Comparing the effectiveness of rank correlation statistics, Working Paper n.06/2009, Dept. of Economics and Statistics, Univ. of Calabria, Italy, 2009.
H. Theil, A rank-invariant method of linear and polynomial regression analysis, Part 3, Proceedings of Koninklijke Nederlandse Akademie van Wetenenschappen, 53, 1950, pp. 1397-1412.
M. L. Tiku, W. Y. Tan and N. Balakrishnan, Robust Inferences, Marcel Dekker, Inc., NY, 1986.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Pushpa Publishing House, Prayagraj, India
This work is licensed under a Creative Commons Attribution 4.0 International License.
____________________________
Attribution: Credit Pushpa Publishing House as the original publisher, including title and author(s) if applicable.
No Derivatives: Modifying or creating derivative works not allowed without written permission.
Contact Pushpa Publishing House for more info or permissions.
Journal Impact Factor: 
