Abstract
We propose a new approach to model a sequence of spatially distributed time series of extreme values. Unlike common practice, we incorporate spatial dependence directly in the likelihood and allow the temporal component to be captured at the second level of hierarchy. Inferences about the parameters and spatio-temporal predictions are obtained via MCMC technique. The model is fitted to a gridded precipitation data set collected over 99 years across the continental U.S. © 2010 John Wiley & Sons, Ltd..
Original language | English (US) |
---|---|
Pages (from-to) | 192-204 |
Number of pages | 13 |
Journal | Environmetrics |
Volume | 22 |
Issue number | 2 |
DOIs | |
State | Published - Mar 30 2011 |
Externally published | Yes |
Bibliographical note
KAUST Repository Item: Exported on 2020-10-01Acknowledged KAUST grant number(s): KUS-CI-016-04
Acknowledgements: The first author's research was partially supported by National Science foundation CMG reserach grants DMS-0724704, ATM-0620624, and by Award Number KUS-CI-016-04 made by King Abdullah University of Science and Technology (KAUST). The second author's research was supported by National Science foundation CMG reserach grants ATM-0620624. They gratefully acknowledge two referees for their constructive suggestions that led to significant improvement of the paper.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.