Robust circular-circular correlation coefficient

Ehab A. Mahmood

Communications in Statistics - Theory and Methods, 2024, vol. 53, issue 6, 2034-2042

Abstract: Many classical methods have been proposed to compute circular-circular correlation coefficients. However, these classical methods might be very sensitive to outliers in the data set. To date, no work has suggested a robust method to estimate a circular-circular correlation coefficient. The present paper aims to propose two robust methods to compute a circular-circular correlation coefficient when the circular data has outliers. The first method is computed based on the circular median, rMed, and the second on the circular trimmed mean, rTrim. A simulation study is conducted for two circular distributions: the wrapped normal and wrapped Cauchy distributions. The simulation and practical example show that the results of rMed are close to the results of classical methods. In contrast, the rTrim gives the best results and is the least affected by outliers, even with a high percentage of outliers.

Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/03610926.2022.2117561 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:lstaxx:v:53:y:2024:i:6:p:2034-2042

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/lsta20

DOI: 10.1080/03610926.2022.2117561

Access Statistics for this article

Communications in Statistics - Theory and Methods is currently edited by Debbie Iscoe

More articles in Communications in Statistics - Theory and Methods from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().