Teaching

Spatial and spatio-temporal statistics applied to ecology and environment

This is a short introduction to statistical spatio-temporal modeling. It starts with basic concepts related to hierarchical modeling in a spatio-temporal context before moving to specific notions regarding the specification of the spatial and spatio-temporal variance-covariance function. Some inference methods are also described (kriging, maximum likelihood method and Bayesian inference with a focus on INLA). Some codes are presented as an introduction to R-INLA, a R package to infer spatial and spatio-temporal models based on Bayesian inference. Here are the slides and the related codes.


These slides are mainly based on:

  • Wikle, C. K., Zammit-Mangion, A., & Cressie, N. Spatio-temporal Statistics with R. Chapman and Hall/CRC, 2019. link

  • Krainski, Elias, et al. Advanced spatial modeling with stochastic partial differential equations using R and INLA. Chapman and Hall/CRC, 2018. link

  • Cressie, Noel, and Christopher K. Wikle. Statistics for spatio-temporal data. John Wiley & Sons, 2015.

  • a workshop provided by Thomas Opitz and Denis Allard at Rochebrune. link


Workshop on R-INLA

This is a short introduction to the R-INLA tool, a R package to infer spatial and spatio-temporal models through Bayesian inference. It first describes the global structure of the models implemented in R-INLA. Second, it introduces the SPDE approach and the Integrated Nested Laplace Approximation, two methods implemented in R-INLA to ease the computation burden related to spatial and spatio-temporal model inference. Here are the slides and the related codes.


These slides are mainly based on:

  • Krainski, Elias, et al. Advanced spatial modeling with stochastic partial differential equations using R and INLA. Chapman and Hall/CRC, 2018. link

  • a workshop provided by Thomas Opitz and Denis Allard at Rochebrune. link