Discriminant Analysis for the von Mises-Fisher Distribution

• Tipo: Artigo em Revista Científica Internacional
• Data: 2009

Autores

Adelaide Figueiredo (Autor) FEP

Revista

Título: Communications in Statistics Part B: Simulation and Computation

Vol. 38

Páginas: 1991-2003

ISSN: 0361-0918

Editora: Taylor & Francis

Indexação

ISI Web of Knowledge - 9 Citações

ISI Web of Science

Scopus - 10 Citações

Classificação Científica

FOS: Ciências exactas e naturais

Outras Informações

ID Authenticus: P-003-PFD

DOI: 10.1080/03610910903200281

Abstract (EN): The von Mises-Fisher distribution is widely used for modeling directional data. In this article, we derive the discriminant rules based on this distribution to assign objects into pre-existing classes. We determine a distance between two von Mises-Fisher populations and we calculate estimates of the misclassification probabilities. We also analyze the behavior of the distance between two von Mises-Fisher populations and of the estimates of the misclassification probabilities when we modify the parameters of the populations or the samples size or the dimension of the sphere. Finally, we present an example with real spherical data available in the literature.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 13