Premium
On non‐parametric measures of correlation for directional data
Author(s) -
Alvo Mayer
Publication year - 1998
Publication title -
environmetrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.68
H-Index - 58
eISSN - 1099-095X
pISSN - 1180-4009
DOI - 10.1002/(sici)1099-095x(199811/12)9:6<645::aid-env328>3.0.co;2-b
Subject(s) - statistics , correlation , mathematics , parametric statistics , econometrics , geometry
Rank correlation measures are defined for directional data based on measures of distance. Angular–angular as well as angular–linear correlations are considered. Asymptotic distributions are obtained for statistics based on Spearman and Kendall measures under the null hypothesis of no association. The results are applied to two sets of data. The first consists of pairs of wind directions, whereas the second involves data on wind directions and ozone. Copyright © 1998 John Wiley & Sons, Ltd.