RESEARCH ARTICLE
Linear and Directional Domains with Cauchy Probability Distributions
T. D. Downs*, K. J. Downs
Article Information
Identifiers and Pagination:
Year: 2012Volume: 4
First Page: 5
Last Page: 10
Publisher Id: TOSPJ-4-5
DOI: 10.2174/1876527001204010005
Article History:
Received Date: 12/5/2012Revision Received Date: 25/6/2012
Acceptance Date: 28/6/2012
Electronic publication date: 20/9/2012
Collection year: 2012
open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Abstract
The usual domains for Cauchy distributions have been straight lines and unit circles. These domains are closed under arbitrary changes in location and scale, whether done sequentially or simultaneously. Such closure properties have been extended to spherical Cauchy distributions. Higher dimensional Cauchy-based domains are created herein for unit hyperspheres and sets of straight lines of arbitrary dimension, and their Cauchy-like properties are determined and described. Cauchy distributions on these extended domains are shown to be closed under arbitrary transformations of location and scale, done singly or sequentially, but not generally closed when location and scale changes are done simultaneously. Stereographic projections are used to map the curved, finite surface of any hypersphere to a linear, infinite space of the same dimension as that of the hyperspherical surface. These mappings are one-one and onto, with no loss of information. These results show promise for uniting linear and directional mixtures of observations into a common domain-linear or directional.