This is a short course of the Mathematics for daTa scieNce study plan

Tobia Filosi

(University of Trento)

Bio

Tobia Filosi is a PhD student at the mathematics department of the Trento University. He is currently working on definition and estimation of kernels on graphs with Euclidean edges in space and space-time, as well as efficient methods for simulation of stochastic processes on such domains.

Course Description

In this course, a brief introduction about spatial and spatio-temporal statistics will be given. First, we will have a look at the different spatial data that are usually encountered in spatial statistics. Afterwards, we will focus on geostatistical processes and discuss their basic concepts, e.g. spatial covariance functions and variograms, and geometric properties. In addition, kriging (i.e. optimal linear unbiased prediction for geostatistical processes) methodology will be presented. Hopefully, we will be able to touch some spatio-temporal topics in the final lecture.

List of topics

Introduction
- Spatial data-types
- Modelling through hierarchical models
Properties of geostatistical processes
- Basic concepts
- Covariance functions
- Variograms
- Geometric properties
Modelling geostatistical processes
- Introduction
- Kriging
Introduction about spatio-temporal statistical models
- Spatio-temporal covariance functions

References

Cressie, N., & Wikle, C.K. (2011). Statistics for Spatio-Temporal Data.

Schedule

Thursday 12 December 2024, 08.30-10.30 room A219
Tuesday 17 December 2024, 15.30-17.30 room A203
Thursday 19 December 2024, 08.30-10.30 room A219

Details

Venue: Polo Scientifico e Tecnologico F. Ferrari
Language: English
The participation is free. Please send an email to Prof. Claudio Agostinelli to confirm your participation.
For further information, please contact Prof. Claudio Agostinelli