Lung cancer cases and population at risk in the 67 counties of Pennsylvania in 2002, by race, sex and age group, with each county's smoking rate. The rate cases / population varies with the strata, with smoking, and between neighbouring counties; pennlc_adj gives the counties' contiguity.
Format
A data frame with 1072 rows (67 counties x 2 races x 2 sexes x 4 age groups) and 9 columns:
- county
County name, lower case; the row names of pennlc_adj.
- race
"white"or"other".- sex
"female"or"male".- age
Age group:
"<40","40-59","60-69"or"70+".- cases
Lung cancer cases in 2002.
- population
Population of the stratum. One stratum (Cameron county, other race, female, 70+) has none, and no cases.
- lon, lat
Longitude and latitude of the county centroid.
- smoking
Proportion of smokers in the county.
Source
The pennLC data of the SpatialEpi package (version 1.2.8), from
the Pennsylvania Department of Health (cases and population) and the
Behavioral Risk Factor Surveillance System (smoking). The build script is
data-raw/pennlc.R in the package's source repository.
Examples
head(pennlc)
#> county race sex age cases population lon lat smoking
#> 1 adams white female <40 0 23351 -77.2155 39.87776 0.234
#> 2 adams white female 40-59 5 12136 -77.2155 39.87776 0.234
#> 3 adams white female 60-69 5 3609 -77.2155 39.87776 0.234
#> 4 adams white female 70+ 18 5411 -77.2155 39.87776 0.234
#> 5 adams white male <40 0 23602 -77.2155 39.87776 0.234
#> 6 adams white male 40-59 4 11844 -77.2155 39.87776 0.234
# Crude rate per 100,000 by age group
with(pennlc, tapply(cases, age, sum) / tapply(population, age, sum) * 1e5)
#> <40 40-59 60-69 70+
#> 0.9343567 56.6882331 258.7895742 400.9012109