Summer School on Topics in Space-Time Modeling and Inference

May 27 2013 - 14:44
May 31 2013 - 14:44
Venue: 

Aalborg University, Denmark

Short description of the event: 

Lecturers:
Professor Peter Diggle, Lancaster University
Professor Tilmann Gneiting, University of Heidelberg
Professor Peter F. Craigmile, Ohio State University
Professor Rasmus Waagepetersen, Aalborg University.

Organizer: Professor Jesper Møller, Department of Mathematical Sciences, Aalborg University, in collaboration with www.csgb.dk

Professor Peter Diggle, Lancaster University, will give a simple classification of space-time point processes and/or data according to whether the spatial or temporal dimension (but not both!) is discrete, and argue that these different situations require different approaches to statistical analysis, and that the choice of modelling strategy should be influenced by the scientific goals of the study that generated the data for analysis. He will also describe statistical models, methods and R packages for space-time point process data.
Professor Tilmann Gneiting, University of Heidelberg, will discuss the correlation theory of stochastic processes on Euclidean domains and spheres, which offers a wide range of challenging open problems. Applications and case studies in weather and climate research call for an increased involvement of probabilists and statisticians in the atmospheric sciences.
Professor Peter F. Craigmile, Ohio State University, will introduce spectral- and wavelet-based methods that can be applied to temporal, spatial, and spatio-temporal data. Topics include time-frequency representations, model construction, and approximate methods of inferences for spatio-temporal processes.
Professor Rasmus Waagepetersen, Aalborg University, will consider statistical models and methods for spatial point processes. His lectures will provide an introduction to spatial Gibbs and Cox point processes and to various approaches to inference for spatial point processes including summary statistics, estimating functions and maximum likelihood estimation.

The mode of presentations will be a combination of lectures, software demonstration and, for those who have their own computers loaded with the R software, opportunities to try the methods for themselves.

Deadline: for registration is 1 February 2013.

Credits: PhD ECTS: 2.5 ECTS for participating and additional 2.5 ECTS if you present a poster at the summer school and write a small report on how the topics covered in the course relate to your own PhD project.