Por favor, use este identificador para citar o enlazar este ítem:
http://cimat.repositorioinstitucional.mx/jspui/handle/1008/702| Generalised Natural Conjugate Prior Densities : Singular Multivariate Linear Model | |
| JOSE ANTONIO DIAZ GARCIA | |
| Acceso Abierto | |
| Atribución-NoComercial | |
| Inferencia Bayesiana | |
| In the classical approach of statistics, the multivariate linear model under dif- ferent kinds of singularities, has been studied by a number of authors, see for example, Khatri (1968) and Srivastava and Khatri [pp. 174-175] (1979). In the area of Bayesian inference, the nonsingular multivariate linear model has been considered using both noninformative and informative priors, by, among oth- ers, Box and Tiao [Chapter 8] (1979) and Press[Section 8.6] (1982). However, due to the inherent difficulties when dealing with probability distributions of singular random matrices, the multivariate linear model had not been studied from a bayesian point of view when there are singularities in its parameters. Recently, D ́ıaz-Garc ́ıa et al (2003a) have approached the subject of Bayesian in- ference for the singular multivariate linear model using noninformative priors, also they have treated informative priors for inference on covariance matrices, see Díaz-García et al(2003b). | |
| Centro de Investigación en Matemáticas AC | |
| 06-05-2003 | |
| Reporte | |
| Inglés | |
| Investigadores | |
| FUNDAMENTOS DE LA INFERENCIA ESTADÍSTICA | |
| Versión publicada | |
| publishedVersion - Versión publicada | |
| Aparece en las colecciones: | Reportes Técnicos - Probabilidad y Estadística |
Cargar archivos:
| Fichero | Tamaño | Formato | |
|---|---|---|---|
| I-03-11.pdf | 251.65 kB | Adobe PDF | Visualizar/Abrir |