Earth data
Global Sunrise & Sunset Data:
Description: Global pixel level, daily data of the sunrise and sunset time from 1700 to present.
Python code: Modify the Python code to scrape the data in any location and any period.
Stata code: Modify the Stata code to clean above scraped data.
Source: U.S. Navel Observatory
Global Temperature Data:
Description: Global pixel level, daily data of the average, minimum, maximum temperature from 1979 to present.
Python code: Modify the Python code to transfer the original NetCDF format data to CSV.
Stata code: Modify the Stata code to merge and clean above CSV data.
Source: Climate Prediction Center Global Temperature Time Series
Internet data
Google Search Index Data:
Description: Monthly to minutely, country to city level data of search index of selected keywords in all countries from 2004 to latest date.
Python code: Modify the Python code to scrape the search index of any keyword in any region in any time from 2004.
Source: Google trends
Note: The search index data could be used to predict latest trends or as outcome variables to measure intention. Daily, hourly, minutely level data only available in past 90 days, past 7 days, and past 4 hours, respectively
National data
Finland municipality data:
Description: Annual, municipal level data of health, crimes, socio-economic outcomes, and so on in 305 Finnish municipalities from 1990 to 2018.
Data: Please ask via email.
Paper: The Effects of Alcohol Consumption on Health, Crimes, and Socio-economic Outcomes