SciELO - Scientific Electronic Library Online

 
vol.34 número3Una aplicación de los modelos semi-markovianos al problema de la ruinaEstimación del costo de garantía descontado para un sistema coherente bajo reparo mínimo índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados

Revista

Articulo

Indicadores

Links relacionados

  • En proceso de indezaciónCitado por Google
  • No hay articulos similaresSimilares en SciELO
  • En proceso de indezaciónSimilares en Google

Compartir


Revista Colombiana de Estadística

versión impresa ISSN 0120-1751

Resumen

BRAN-CARDONA, PAULA ANDREA; OROZCO-CASTANEDA, JOHANNA MARCELA  y  NAGAR, DAYA KRISHNA. Bivariate Generalization of the Kummer-Beta Distribution. Rev.Colomb.Estad. [online]. 2011, vol.34, n.3, pp.497-512. ISSN 0120-1751.

In this article, we study several properties such as marginal and conditional distributions, joint moments, and mixture representation of the bivariate generalization of the Kummer-Beta distribution. To show the behavior of the density function, we give some graphs of the density for different values of the parameters. Finally, we derive the exact and approximate distribution of the product of two random variables which are distributed jointly as bivariate Kummer-Beta. The exact distribution of the product is derived as an infinite series involving Gauss hypergeometric function, whereas the beta distribution has been used as an approximate distribution. Further, to show the closeness of the approximation, we have compared the exact distribution and the approximate distribution by using several graphs. An application of the results derived in this article is provided to visibility data from Colombia.

Palabras clave : Beta distribution; Bivariate distribution; Dirichlet distribution; Hypergeometric function; Moments; Transformation.

        · resumen en Español     · texto en Inglés     · Inglés ( pdf )

 

Creative Commons License Todo el contenido de esta revista, excepto dónde está identificado, está bajo una Licencia Creative Commons