A semi-parametric model for circular data based on mixtures of beta distributions

• Autores: Michael Peter Wiper, José Antonio Carnicero Carreño
• Localización: XXX Congreso Nacional de Estadística e Investigación Operativa y de las IV Jornadas de Estadística Pública: actas, 2007, ISBN 978-84-690-7249-3
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • In this paper, we introduce a new, semi-parametric model for circular data based on mixtures of scaled, shifted beta distributions. An advantage of our approach is that it can fit asymmetric and multimodal data sets well in contrast with many standard models in this field. Furthermore, this model includes the (scaled, shifted) Bernstein polynomial densities as a special case and these are well known to provide good approximations to any density with finite range. A classical, maximum likelihood approach is used to fit the model and the results are illustrated with two real data examples which compare the suggested model with Bernstein polynomials and with mixtures of von-Mises densities.