I have statistical data for a certain region based on a subdivision of that region into districts (e.g. number of schools per district). Now I want to resample that data to a different subdivision of the same region. The two subdivisions don't have anything in common aside from covering the same overall region.

My specific use case is to resample statistics based on city districts to voting districts. I have the outlines of the districts in two GeoJSON files (one for the city districts, one for the voting districts). The former also contains the statistics I want to resample (as properties of the GeoJSON features). Resampling based on the area shared between the two types of districts would be a good start, although I'd love to take the population count of the voting districts into account, too (that information is available in the second GeoJSON file).

  • Please provide more specifics on your problem to have it reopened but, I would urge you to look at the statistical issues of ecological fallacy and MAUP as the both are directly relevant to what you have in mind. – Jeffrey Evans Sep 13 '17 at 13:26
  • @JeffreyEvans Thanks for the pointers! I will keep them in mind during the analysis. – Florian Brucker Sep 14 '17 at 7:26

In the meantime I have found CoGran, an open source command-line tool that does exactly what I need.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.