Posts
SICSS-Covenant:Using gridded population to gain spatial insights in R
I have been invited to present at the Summer Institute for Computational Social Sciences in University of Covenant. My talks starts is about gridded population as a tool to link demographics and geography. It starts with a global overview of the definition, production and use of this innovative data and pursues with a hands-on in R to gain spatial insights on demography in Nigeria.
Efficient computation across multiple rasters
One day you want to compute one quantile across 95 rasters, and suddenly your script takes 7 hours to run, luckily at night. And then you're facing the truth: you will have to dig into the stars R-package. But to this date, few implementations lie around. So we share here one demonstration of the efficiency of stars with a special big up for the st_apply function.
Which population microdata are openly accessible?
Population microdata are key input to estimate and map population. They are however often difficult to access when derived from household survey pre-listings: (1) because of the limited number of household survey (2) because of the confidentiality of cluster locations (3) because it is operationnal data that is not cleaned and stored appropriately for reuse. We explore in this blog post the availibility of two promising datasets for population modelling: IPUMS-International and the Demographic and Health Surveys programm.
How to get a clear view of hierarchical data? Answer: Sunburst Charts
Sunburst charts are a great tool to visualise hierarchichal data structure and unravel missing combinations. Useful as an exploratory analysis for Bayesian hierarchical models.
How fine can a top-down population model be? [draft]
We will study the use of very high-resolution covariates in top-down population model and its impact on population gridded estimates. We will examine building-footprint derived covariates in Sierra Leone population model. Disclaimer: This post is still being drafted.
