Paula Moraga: Spatial modeling and interactive visualization with the R-INLA package

Lecturer: Paula Moraga. King Abdullah University of Science and Technology (KAUST)
Summary:
We will learn how to develop and interpret spatial models with R-INLA (www.r-inla.org), and how to create maps and other visualizations to facilitate the communication with collaborators and policymakers. The course is hands-on with three parts:
- Introduction to geospatial data and R-INLA
- Modeling areal data (lung cancer risk in Pennsylvania, USA)
- Modeling geostatistical data (malaria prevalence in The Gambia)
We will focus on health applications but the methods covered are applicable to many other fields that deal with georeferenced data such as ecology, demography or criminology
Slides: www.paulamorag...
Installing R packages:
install.packages(c("sp", "spdep", "raster", "rgdal", "rgeos", "ggplot2", "leaflet", "DT", "dplyr", "SpatialEpi", "geoR"))
install.packages("INLA", repos = "inla.r-inla-do...", dep = TRUE)
References
Moraga, P. Geospatial Health Data: Modeling and Visualization with R-INLA and Shiny. Chapman & Hall/CRC. ISBN 9780367357955 (2019). www.paulamorag...
How to cite this video:
doi.org/10.5446...

[@klaows]

She's so inspired. Her teaching is so simply but powerful. I really appreciate how she explains is. I tried to attend the INLA vdo on KZbin. Finally, her presentation is so useful and stop me to keep my eyes on her. Thank you very much. Her website and profile are so strong. xoxo.

[@jomath5790]

I'm just going through your text of geospatial health data, it's so interesting.

[@aybukekoyuncu9328]

What if you wanted to use the fitted values to generate a summary for the entire state? How would you get the confidence interval?

[@123sobrasadadepayes]

For the example of Pennsylvania, how can I use a categorical explanatory variable? For example, smoking in 5 categories (low-low, medium-low, medium, medium-high, high-high) Thanks!

[@haraldurkarlsson1147]

dplyr's count does a nice job of aggreating - like this: pennLC$data %>% count(county, wt = cases, name = "cases")