Bayesian joint modelling of the mean and covariance structures for normal longitudinal data
We consider the joint modelling of the mean and covariance structures for the general antedependence model, estimating their parameters and the innovation variances in a longitudinal data context. We propose a new and computationally efficient classic estimation method based on the Fisher scoring al...
| Autores: | , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2007 |
| País: | España |
| Institución: | Universitat Autònoma de Barcelona |
| Repositorio: | Dipòsit Digital de Documents de la UAB |
| Idioma: | inglés |
| OAI Identifier: | oai:ddd.uab.cat:97489 |
| Acceso en línea: | https://ddd.uab.cat/record/97489 |
| Access Level: | acceso abierto |
| Palabra clave: | Antedependence models Bayes estimation Fisher scoring Gibbs sampling |
| Sumario: | We consider the joint modelling of the mean and covariance structures for the general antedependence model, estimating their parameters and the innovation variances in a longitudinal data context. We propose a new and computationally efficient classic estimation method based on the Fisher scoring algorithm to obtain the maximum likelihood estimates of the parameters. In addition, we also propose a new and innovative Bayesian methodology based on the Gibbs sampling, properly adapted for longitudinal data analysis, a methodology that considers linear mean structures and unrestrictedcovariance structures for normal longitudinal data. We illustrate the proposed methodology and study its strengths and weaknesses by analyzing two examples, the race and the cattle data sets. |
|---|