COMPARING THE EFFECTIVENESS OF RANK CORRELATION STATISTICS

Rank correlation is a fundamental tool to express dependence in cases in which the data are arranged in order. There are, by contrast, circumstances where the ordinal association is of a nonlinear type. In this paper we investigate the effectiveness of several measures of rank correlation. These measures have been divided into three classes: conventional rank correlations, weighted rank correlations, correlations of scores. Our findings suggest that none is systematically better than the other in all circumstances. However, a simply weighted version of the Kendall rank correlation coefficient provides plausible answers to many special situations where intercategory distances could not be considered on the same basis.

[1]  A. Mango.  A Distance Function for Ranked Variables: A Proposal for a New Rank Correlation Coefficient , 2006 .

[2]  Philip L. H. Yu,et al.  Distance-based tree models for ranking data , 2010, Comput. Stat. Data Anal..

[3]  Sanford Weisberg,et al.  Computing science and statistics : proceedings of the 30th Symposium on the Interface, Minneapolis, Minnesota, May 13-16, 1998 : dimension reduction, computational complexity and information , 1998 .

[4]  D. Quade,et al.  THE SYMMETRIC FOOTRULE , 2001 .

[5]  R. Iman,et al.  A measure of top-down correlation , 1987 .

[6]  Shree K. Nayar,et al.  Ordinal measures for visual correspondence , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Nils Blomqvist,et al.  On a Measure of Dependence Between two Random Variables , 1950 .

[8]  Note on a Test of Monotone Association Insensitive to Outliers , 1980 .

[9]  Yeung Sam Hung,et al.  Order Statistics Correlation Coefficient as a Novel Association Measurement With Applications to Biosignal Analysis , 2007, IEEE Transactions on Signal Processing.

[10]  M. Kendall.  A NEW MEASURE OF RANK CORRELATION , 1938 .

[11]  P. Moran.  A Curvilinear Ranking Test , 1950 .

[12]  J. Gower.  A General Coefficient of Similarity and Some of Its Properties , 1971 .

[13]  E. Regazzini,et al.  On the asymptotic distribution of a general measure of monotone dependence , 1996 .

[14]  H. Theil.  A Rank-Invariant Method of Linear and Polynomial Regression Analysis , 1992 .

[15]  C. Genest,et al.  On blest's measure of rank correlation , 2003 .

[16]  Grace S. Shieh.  A weighted Kendall's tau statistic , 1998 .

[17]  R. A. Hollister,et al.  A Rank Correlation Coefficient Resistant to Outliers , 1987 .

[18]  Dana Quade,et al.  A nonparametric comparison of two multiple regressions by means of a weighted measure of correlation , 1982 .

[19]  Pitman Efficiency of Independence Tests Based on Weighted Rank Statistics , 2003 .

[20]  D. Blest.  Theory & Methods: Rank Correlation — an Alternative Measure , 2000 .

[21]  C. Spearman.  The proof and measurement of association between two things. By C. Spearman, 1904. , 1987, The American journal of psychology.

[22]  C. L. Mallows,et al.  Some Aspects of the Random Sequence , 1965 .

[23]  J. Costa,et al.  A WEIGHTED RANK MEASURE OF CORRELATION , 2005 .

[24]  Yeung Sam Hung,et al.  Asymptotic Properties of Order Statistics Correlation Coefficient in the Normal Cases , 2008, IEEE Transactions on Signal Processing.

[25]  E. S. Pearson,et al.  TESTS FOR RANK CORRELATION COEFFICIENTS. I , 1957 .

[26]  Christian Genest,et al.  Locally most powerful rank tests of independence for copula models , 2005 .