Abstract
Spearman’s rank correlation coefficient is not entirely suitable to measure the correlation between two rankings in some applications because it treats all ranks equally. In 2001, we have proposed a weighted rank measure of correlation that weights the distance between two ranks using a linear function of those ranks, giving more importance to higher ranks than lower ones. In this chapter, we analyze its distribution and provide a table of critical values to test whether a given value of the coefficient is significantly different from zero. We also summarize a number of applications for which the new measure is more suitable than Spearman’s.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We assume that the higher rank is 1, and corresponds to the “best” element in the ranking.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2015 The Author(s)
About this chapter
Cite this chapter
Pinto da Costa, J. (2015). The Weighted Rank Correlation Coefficient \(r_W\) . In: Rankings and Preferences. SpringerBriefs in Statistics. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-48344-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-662-48344-2_2
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-48343-5
Online ISBN: 978-3-662-48344-2
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)