Online course 8. Regression models with spatial correlation using R-INLA

spatialinla_turtle
£ 500.00 each

+

Flyer for this course

See the online flyer for a detailed description.

 

General outline

We begin with an introduction how to add dependency to regression models using frequentist tools. After discussing the limitations of this approach we switch to Bayesian techniques. R-INLA is used to implement regression models, generalised linear models (GLM) and generalised linear mixed-effects models (GLMM) with spatial dependency.

We will also explain how to deal with dependency around islands and fjords (barrier models). We will use geostatistical data and areal data.

All exercises are executed in R-INLA.

 

Detailed outline

Module 1 consists of 5 on-demand videos

  • General introduction.
  • Theory presentation on adding dependency to a regression model using frequentist techniques: Temporal correlation, spatial correlation and mixed-effects models.
  • One exercise.
  • Short introduction to mixed effects models.
  • One exercise on linear mixed effects models.

Module 2 consists of 5 on-demand videos

  • Brief introduction to Bayesian analysis.
  • Conjugate priors.
  • Diffuse versus informative priors.
  • Theory presentation on INLA.
  • Exercise showing how to execute a linear regression model in R-INLA.

Module 3 consists of 4 on-demand videos

  • Exercise showing how to execute a linear mixed-effects model in R-INLA.
  • Exercise showing how to execute a Poisson GLM in R-INLA.
  • Exercise showing how to execute a negative binomial GLM in R-INLA.
  • Exercise showing how to execute a Bernoulli GLM in R-INLA.

Module 4 consists of 3 on-demand video files

  • Theory presentation on adding spatial correlation to regression models in R-INLA.
  • Exercise showing how to add spatial correlation to a linear regression model.
  • Exercise showing how to add spatial correlation to a Poisson GLM.

Module 5 consists of 4 on-demand video files

  • Exercise showing how to add spatial correlation to a negative binomial GLM.
  • Exercise showing how to add spatial correlation to a Bernoulli GLM.
  • Exercise showing how to add spatial correlation to a gamma GLM.
  • Exercise showing how to add spatial correlation to a beta GLM.

Module 6 consists of 3 on-demand video files

  • Theory presentation on barrier models for dealing with islands and fjords.
  • Two exercises showing how to implement the barrier model.

Module 7 consists of 3 on-demand video files

  • Theory presentation on the analysis of lattice and areal data.
  • Exercise showing how to use the CAR correlation with a Poisson GLM.

See also: https://courses.highstat.com/index.php/online-glm-spatial-correlation

 

Free 1-hour face-to-face video meeting

The course fee includes a 1-hour face-to-face video meeting with one or both instructors. The meeting needs to take place within 12 months after the last live zoom meeting. You can discuss your own data but we strongly suggest that the statistical topics are within the content of the course. The 1-hour needs to be used in one session and will take place on a mutually convenient day.

 

Course material

Pdf files of all presentations are provided. These files are based on various chapters from:

  • Zuur, Ieno, Saveliev (2017). Beginner's Guide to Spatial, Temporal and Spatial-Temporal Ecological Data Analysis with R-INLA.

This book is exclusively available from www.highstat.com. This book is not included in the course fee. The course can be followed without purchasing this book.

Pre-required knowledge

Good knowledge of R, data exploration, linear regression and GLM (Poisson, negative binomial, Bernoulli). Working knowledge of mixed-effects models. Short revisions are provided. This is a non-technical course.