In this paper, we define and discuss a class of generalized Wishart distributions under elliptical models. We derive the non-central moments of the likelihood ratio statistic for testing the equality of two covariance matrices under elliptical models for the corresponding matrices. Known classical e...

Full description

Autores:
Tipo de recurso:
Fecha de publicación:
2014
Institución:
Universidad de Medellín
Repositorio:
Repositorio UDEM
Idioma:
eng
OAI Identifier:
oai:repository.udem.edu.co:11407/1347
Acceso en línea:
http://hdl.handle.net/11407/1347
Palabra clave:
Elliptical models
H-function
Likelihood ratio statistic
Mellin transform
Zonal polynomials
Rights
restrictedAccess
License
http://purl.org/coar/access_right/c_16ec
Description
Summary:In this paper, we define and discuss a class of generalized Wishart distributions under elliptical models. We derive the non-central moments of the likelihood ratio statistic for testing the equality of two covariance matrices under elliptical models for the corresponding matrices. Known classical expressions for the Gaussian model are then deduced from these general results. Finally, the exact distribution of the Wilks’ statistic under a specific distribution, including the Gaussian distribution as a particular member, is derived.