A possibly asymmetric multivariate generalization of the Möbius distribution for directional data

Kagumi Uesu, Kunio Shimizu and Ashis SenGupta

Journal of Multivariate Analysis, 2015, vol. 134, issue C, 146-162

Abstract: A family of possibly asymmetric distributions on the unit hyper-disc with center at the origin is proposed. The paper presents a non-trivial multivariate generalization of the Möbius distribution on the unit disc. The family is obtained by applying a conformal mapping to the spherically symmetric beta distribution. The density functions of the family are unimodal, monotonic or uniantimodal. The conditional distribution of direction cosine given the length is a t-distribution on the sphere. The conditional distribution of the length given the direction cosine has a simple closed form expression, though not of any standard known distribution. Modality, skewness and direction parameters are globally orthogonal in the sense that the Fisher information matrix is diagonal. The proposed model on the hyper-disc, introducing this probability distribution for the very first time, is applied to an emerging area of astrophysics for a dataset on gamma-ray bursts and to a challenging area of geoinformatics for a dataset on worldwide earthquakes with magnitude greater than or equal to 7.0MW.

Keywords: Hyperbolic space; Möbius transformation; Spherically symmetric beta distribution; Stereographic projection (search for similar items in EconPapers)
Date: 2015
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0047259X14002590
Full text for ScienceDirect subscribers only

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:eee:jmvana:v:134:y:2015:i:c:p:146-162

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

DOI: 10.1016/j.jmva.2014.11.004

Access Statistics for this article

Journal of Multivariate Analysis is currently edited by de Leeuw, J.

More articles in Journal of Multivariate Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().