Author:
Zinhom E.,Nassar M. M.,Radwan S. S.,Elmasry A.
Abstract
AbstractIn the study of many environmental phenomena, circular statistical analysis and applications to directional data are crucial. In this paper, we introduce the wrapped XLindley distribution, a novel circular distribution with a single parameter. We derive expressions for the distribution’s characteristic function, trigonometric moments, and other associated descriptive measures. The unknown distributional parameter is estimated using the maximum likelihood, least squares, and weighted least squares approach, and the accuracy of these estimates is tested using a simulation study. Finally, to clarify the suggested distribution’s modeling potential, we fit the proposed model to two circular real-world data sets and evaluate the goodness of fit of this distribution in comparison to the wrapped Lindley, wrapped modified Lindley, Von Mises, Jones–Pewsey, and Kato–Jones distributions.
Publisher
Springer Science and Business Media LLC
Subject
Statistics, Probability and Uncertainty,General Environmental Science,Statistics and Probability
Reference28 articles.
1. Al-khazaleh A (2021) Wrapped Akash distribution. Electron J Appl Stat Anal 14(2):305–317
2. Bahnsen AC, Stojanovic A, Aouada D, Ottersten B (2014) Improving credit card fraud detection with calibrated probabilities. In: Proceedings of the 2014 SIAM international conference on data mining, 2014. SIAM, pp 677–685
3. Bahnsen AC, Acevedo J, Salcedo-Gallo JS, Villegas S, Solano J (2023) pycircular: v0.1
4. Bhattacharjee S, Ahmed I, Das KK (2021) Wrapped two-parameter Lindley distribution for modelling circular data. Thail Stat 19(1):81–94
5. Capaccioni B, Valentini L, Rocchi MB, Nappi G, Sarocchi D (1997) Image analysis and circular statistics for shape-fabric analysis: applications to lithified ignimbrites. Bull Volcanol 58(7):501–514