EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Empirical Evaluation of the Relative Range for Detecting Outliers

Dania Dallah iD, Hana Sulieman iD, Ayman Al Zaatreh iD, Firuz Kamalov iD

Entropy · 07.07.2025 · 27 (7) · 731

DOI: 10.3390/e27070731 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 07.07.2025. Verfasst von Dania Dallah und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics and Statistics, American University of Sharjah, Sharjah 26666, United Arab Emirates. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: American University of Sharjah (AUS), AUS Faculty research grant.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Outlier detection plays a key role in data analysis by improving data quality, uncovering data entry errors, and spotting unusual patterns, such as fraudulent activities. Choosing the right detection method is essential, as some approaches may be too complex or ineffective depending on the data distribution. In this study, we explore a simple yet powerful approach using the range distribution to identify outliers in univariate data. We compare the effectiveness of two range statistics: we normalize the range by the standard deviation (σ) and the interquartile range (IQR) across different types of distributions, including normal, logistic, Laplace, and Weibull distributions, with varying sample sizes (n) and error rates (α). An evaluation of the range behavior across multiple distributions allows for the determination of threshold values for identifying potential outliers. Through extensive experimental work, the accuracy of both statistics in detecting outliers under various contamination strategies, sample sizes, and error rates (α=0.1,0.05,0.01) is investigated. The results demonstrate the flexibility of the proposed statistic, as it adapts well to different underlying distributions and maintains robust detection performance under a variety of conditions. Our findings underscore the value of an adaptive method for reliable anomaly detection in diverse data environments.

Schlagwörter

Stichwörter der Autor:innen

data analysisorder statisticoutlier detectionrange distribution

Autor:innen und Institutionen

  • Department of Mathematics and Statistics, American University of Sharjah, Sharjah 26666, United Arab Emirates.
  • School of Engineering, Applied Science and Technology, Canadian University Dubai, Dubai 14143, United Arab Emirates.

ORCID-Profile: Dania Dallah, Hana Sulieman, Ayman Al Zaatreh, Firuz Kamalov

Förderung

  • American University of Sharjah (AUS)
  • AUS Faculty research grant

Zitieren

APA

Dallah, D., Sulieman, H., Zaatreh, A. A., & Kamalov, F. (2025). Empirical Evaluation of the Relative Range for Detecting Outliers. Entropy, 27(7), 731. https://doi.org/10.3390/e27070731

Vancouver

Dallah D, Sulieman H, Zaatreh AA, Kamalov F. Empirical Evaluation of the Relative Range for Detecting Outliers. Entropy. 2025;27(7):731. doi:10.3390/e27070731

BibTeX
@article{Dallah2025,
  author = {Dallah, Dania and Sulieman, Hana and Zaatreh, Ayman Al and Kamalov, Firuz},
  title = {Empirical Evaluation of the Relative Range for Detecting Outliers},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {7},
  pages = {731},
  doi = {10.3390/e27070731}
}
Kostenlos starten →