0

I'm looking for public datasets that have a sort of "discontinuity" in them. Ideally, this discontinuity should be Coronavirus, and we should see a change in the distribution of the data after this discontiuity.

Any references would be greatly appreciated!

2
  • can you define discontinuity please? ideally provide an example?
    – albert
    May 23 '20 at 18:26
  • 1
    Sure: that the distribution of the data changes. More formally, that you can train a random forest model so that it detects whether the data belongs to pre or post coronavirus successfully May 24 '20 at 10:55
2

It's hard to define "after" since we are still in the middle of it. But the discontinuity surely exists between "before" and "during".

I would suggest something global and clean (machine readable), like the Google Mobility Data, which is available as global or regional CSV files.

https://www.google.com/covid19/mobility/

The data shows how visits to places, such as grocery stores and parks, are changing in each geographic region.

https://www.google.com/covid19/mobility/data_documentation.html?hl=en

1

Perhaps you would be interested in a pre and post COVID-19 look at deaths (spoiler alert: you will notice a sudden increase in deaths in 2020). CDPH has published a query tool for top reportable causes-of-death data by demographic breakdowns with their California Vital Data Query Tool, it is free to register and you can get relatively up-to-date counts of deaths by reportable cause-of-death.

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.