Reference

The 24 September 2020 BMJ Open paper:

The 08 April 2020 rapid response

Dataset and reproducible data analysis

We studied the particulate.csv dataset, which contains 110 observations of 15 variables:

• idStudy, counter ranging from 1 to 110
• idIstat, an integer adopted from Italian National Institute of Statistics
• Province, the name of italian cities/provinces
• itCode, a two character province identifier (primary key)
• Exceedancees, the integer number (absolute frequency) of PM10 concentrations above the daily limit value
• StationsNum, the integer number of the air quality monitoring stations within each province
• Cases, the integer number of infections at sevententh day
• Population, the total residents of the province
• Density, the population over the surface, times 1000 and rounded
• Long, the longitude of the city center
• Lat, the latitude of the city center
• Where, a factor with two levels (north, south) according to the lines joining the towns of Ormea, Fraconalto and San Marino
• Commuters, the integer number of people moving to go to work according the Italian National Institute of Statistics
• CommutersDensity, the Commuters number divided by the Population, times 100 and rounded
• ExcedRatio25, the relative frequency of PM2.5 concentrations above the daily limit value

You can exploit the R language and its party package to reproduce the data analysis following this code.