Statistical and computational methods for the analysis of spatial data

Lines connect the coordinator with its partners.

Project objective

The proposal covers a number of areas of spatial statistics, including There will be seven postdoctoral researchers, most if not all recent PhDs. geostatistical and lattice models, random point processes and stochastic We expect them to visit several centres and pursue joint research with different partners. The benefit to the researchers involved will be geometry problems such as deformable template models and tessellations. participation in a very vigorous area of statistical research with much Major areas of application include imaging, and the use of spatial and opportunity for subsequent employment in academia and in industry. spatial-temporal models in analysing environmental data. WE also consider models ?or spatial data based on mixtures. A common theme is the need for simulation-based methods of data analysis, in particular Markov chain Monte Carlo (MCMC) but also other techniques such as bootstrapping. This in turn leads us into theoretical analysis of MCMC and bootstrapping algorithms. A major theme of the proposed research is the development of original theoretical results for MCMC and bootstrap in the context of spatial models. A final theme is the study of extremal properties of spatial processes, motivated by a number of environmental applications.

Original text from CORDIS.

Participants

• University of Cambridge · CambridgeCoordinatorUnited Kingdom
• Athens University of Economics and Business · AthensGreece
• CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE · PARISFrance
• CHALMERS UNIVERSITY OF TECHNOLOGY · GOETEBORGSweden
• UNIVERSITA DEGLI STUDI DI ROMA TRE · ROMAItaly
• UNIVERSITY OF LANCASTER · LancasterUnited Kingdom
• Ålborg Universitet · ËlborgDenmark

Links

• View on CORDIS