Blockwise Euclidean likelihood for spatio-temporal covariance models

Víctor Morales-Oñate, Federico Crudu () and Moreno Bevilacqua ()

Department of Economics University of Siena from Department of Economics, University of Siena

Abstract: In this paper we propose a spatio-temporal blockwise Euclidean likelihood method for the estimation of covariance models when dealing with large spatio-temporal Gaussian data. The method uses moment conditions coming from the score of the pairwise composite likelihood. The blockwise approach guarantees considerable computational improvements over the standard pairwise composite likelihood method. In order to further speed up computation we consider a general purpose graphics processing unit implementation using OpenCL. We derive the asymptotic properties of the proposed estimator and we illustrate the nite sampleproperties of our methodology by means of a simulation study highlighting the computational gains of the OpenCL graphics processing unit implementation. Finally, we apply our estimation method to a wind component data set.

Keywords: Composite likelihood; Euclidean likelihood; Gaussian random elds; Parallel computing; OpenCL (search for similar items in EconPapers)
JEL-codes: C14 C21 C23 (search for similar items in EconPapers)
Date: 2020-03
New Economics Papers: this item is included in nep-cmp, nep-ecm and nep-ore
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://repec.deps.unisi.it/quaderni/822.pdf (application/pdf)

Related works:
Journal Article: Blockwise Euclidean likelihood for spatio-temporal covariance models (2021)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:usi:wpaper:822

Access Statistics for this paper

More papers in Department of Economics University of Siena from Department of Economics, University of Siena Contact information at EDIRC.
Bibliographic data for series maintained by Fabrizio Becatti ().