Por favor, use este identificador para citar o enlazar este ítem:
http://cimat.repositorioinstitucional.mx/jspui/handle/1008/645| A General Purpose Scale-Independent MCMC Algorithm | |
| JOSE ANDRES CHRISTEN GRACIA | |
| Acceso Abierto | |
| Atribución-NoComercial | |
| Inferencia Bayesiana | |
| We develop a new effectively adaptive, general purpose MCMC for arbitrary continuous distributions and correlation structure. We call this MCMC the t-walk . The t-walk maintains two independent points in the sample space, and all moves are based on proposals that are then accepted with a standard Metropolis-Hastings acceptance probability on the product space. Hence the t-walk may be viewed as an adaptive MCMC sampler that maintains a set of two points in the state space and moves them with some structure. However the t- walk is strictly not adaptive on the product space, but does display beneficial self-adjusting behavior on the original state space. Four proposal distributions, or ‘moves’, are given resulting in an algorithm which is effective in sampling distributions of arbitrary scale, without the requirement for further tuning of parameters. Several examples are presented showing good mixing and convergence characteristics, varying in dimensions from 1 to 200 and with radically different scale and correlation structure, using exactly the samepler. | |
| Centro de Investigación en Matemáticas AC | |
| 12-12-2007 | |
| Reporte | |
| Inglés | |
| Investigadores | |
| ESTADÍSTICA | |
| Versión publicada | |
| publishedVersion - Versión publicada | |
| Aparece en las colecciones: | Reportes Técnicos - Probabilidad y Estadística |
Cargar archivos:
| Fichero | Tamaño | Formato | |
|---|---|---|---|
| I-07-16.pdf | 3.9 MB | Adobe PDF | Visualizar/Abrir |