Model-based geostatistics for public health using R

Learning Outcomes

By the end of the workshop, participants will be able to:

• Understand the key principles of model-based geostatistics
  
• Explore and visualise spatial data using R
  
• Fit and interpret geostatistical models
  
• Carry out geostatistical prediction at both pixel and areal levels

---

R Packages

• Essential: RiskMap, rgeoboundaries, ggplot2, sf, terra, elevatr
  
• Optional: shiny

Install RiskMap in R:

devtools::install_github("giorgilancs/RiskMap")

Install rgeoboundaries in R:

remotes::install_github("wmgeolab/rgeoboundaries")

---

Workshop Content

All R scripts used in the slides can be downloaded

1. Introduction

Geostatistical problems in the context of epidemiological studies.

• Slides

2. Exploratory Analysis

Exploring associations and spatial correlation.

• Slides

• R script

3. Model Formulation and Parameter Estimation

Fitting geostatistical models via Monte Carlo maximum likelihood.

• Slides

• R script

4. Geostatistical Prediction

Prediction of health outcomes at different spatial scales.

• Slides

• R script

---

Using the Materials

• Each section includes slides, R code, and short exercises.
  
• Materials can be followed independently after the workshop.