New advanced outliers detection tests

Alamgir Khalil, Salahuddin, Wali Khan Mashwani, Muhammad Shafiq, Saima Hassan and Wiyada Kumam

Communications in Statistics - Theory and Methods, 2021, vol. 50, issue 7, 1640-1655

Abstract: Outliers have been of constant concern for statistician. These outliers must be handled carefully while analyzing data, particularly, when the data points are measurements based on experiments conducted in scientific labs. Various studies have been conducted on the comparison of outliers detection tests when the data points were assumed to follow normal distribution or skewed exponential or gamma distribution. However, the data may follow some heavy tailed symmetric distribution. One important heavy tailed distribution is Cauchy distribution which has applications in different fields of science including Physics, engineering etc. In the present study, we introduce two tests, in univariate case, for detecting one or more outliers while sampling is done from Cauchy distribution. The proposed tests make use of the robust statistics, namely, median, quartile deviation and the variance based on “sample free of suspected outlier(s)”. We simulate critical values and powers of the tests to compare them with the tests available in the literature. We compare their efficiency using power criteria.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://hdl.handle.net/10.1080/03610926.2020.1741630 (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:50:y:2021:i:7:p:1640-1655

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

DOI: 10.1080/03610926.2020.1741630

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 ().