Spectral-marginal-based estimation of spatiotemporal long-range dependence
- Frías Bustamante, María del Pilar
- Ruiz Medina, María Dolores
- Alonso, Francisco J.
- Angulo Ibáñez, José Miguel
Editorial: Comité organizador del XXX Congreso Nacional de Estadística e Investigación Operativa y IV Jornadas de Estadística Pública
ISBN: 978-84-690-7249-3
Año de publicación: 2007
Congreso: Congreso Nacional de Estadística e Investigación Operativa (30. 2007. Valladolid)
Tipo: Aportación congreso
Resumen
Long-memory and strong spatial dependence are two features which can arise jointly or separately depending on the tail behavior of the temporal and spatial covariance functions of a given spatiotemporal process. Under certain conditions, such a behavior can be related to the behavior of temporal and spatial frequencies in a neighborhood of the origin. In particular, a spatiotemporal process displaying long-memory and/or strong spatial dependence can be built, in terms of separable heavy-tail filters, from a second-order processes satisfying suitable regularity and moment conditions. A parameter estimation method based on the marginal spectral densities is implemented to approximate the long-memory and/or strong-spatial-dependence parameters.