----------------------------------------------------------------------------------------------------------------------
SHORT DESCRIPTIONThis two day free course will cover approximate Bayesian inference for latent Gaussian models using integrated nested Laplace approximations (INLA). A particular focus will be on spatial and spatio-temporal modeling for point and geostatistical processes. The lectures will include also practical examples using the package R-INLA(http://www.r-inla.org/).
The course is sponsored by the StEPhI project (http://stephiproject.it/) within the Futuro in Ricerca (FIRB)
framework (project ID RBFR12URQJ).
----------------------------------------------------------------------------------------------------------------------
INSTRUCTOR
Dr. Daniel Simpson, Department of Mathematical Sciences, Norwegian University of Science and Technology
TENTATIVE PROGRAM
28 October 2013
- 10:30 - 12:30: LGMS
- 14:30 - 18:00: GMRFS AND R-INLA
29 October 2013
- 09:30 - 12:30: Spatial models and SPDEs
- 14:30 - 18:00: SPDEs and case studies
----------------------------------------------------------------------------------------------------------------------
ATTENDEES
The target audience is anyone with basic training
in Bayesian hierarchical models and MCMC (say, via the BUGS language) who wants to learn about a computationally effective alternative to MCMC. The second part of the
course appeals to scientists interested
in spatial and spatiotemporal data.
Each participant should bring a laptop (not provided by the organizers) with the most recent version of R and a working version of
INLA (run source("
http://www.math.ntnu.no/inla/givemeINLA.R") and then
inla.update(testing=TRUE)).
----------------------------------------------------------------------------------------------------------------------
FEE
Participation is free, but registration is required as the number of participants is limited. Please contact the organizers
for information
:
Michela Cameletti (
[log in to unmask])
Francesco Finazzi (
[log in to unmask])
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++