stl_tbl_lead: Blood Lead Test Results in the City of St. Louis, 2010-2015
In chris-prener/stldata: City of St. Louis Data

Description Usage Format Source References Examples

A data set containing blood lead test results as well as race and poverty data for the City of St. Louis by Census Tract. All demographic data are from the 2015 5-year American Community Survey estimates for St. Louis Census Tracts.

1	data(stl_tbl_lead)

A tibble with 106 rows and 15 variables:

geoID: full census tract id number
tractCE: census tract id number
nameLSAD: census tract string
countTested: number of children screened for blood lead levels between 2010 and 2015
pctElevated: percentage of children tested who had blood lead levels greater than or equal to 5 micrograms per deciliter
totalPop: total population estimate, 2015
totalPop_MOE: margin of error for totalPop
white: estimate for white population, 2015
white_MOE: margin of error for white
black: estimate for black population, 2015
black_MOE: margin of error for black
povertyTot: estimate for persons living below poverty line, 2015
povertyTot_MOE: margin of error for povertyTot
povertyU18: estimate for children living below poverty line, 2015
povertyU18_MOE: margin of error for povertyU18

Reuters reporting on lead exposure and 2015 5-year American Community Survey estimates for City of St. Louis Census Tracts via American Fact Finder

Pell, M.B. & Schneyer, J. (2016, December 19). Off the Charts: The thousands of U.S. locales where lead poisoning is worse than in Flint. Reuters, retrieved from website.

str(stl_tbl_lead)
head(stl_tbl_lead)
summary(stl_tbl_lead$pctElevated)
summary(stl_tbl_lead$black)
summary(stl_tbl_lead$povertyTot)

if (require("dplyr") & require("ggplot2")) {

  # what is the relationship between race and lead test results?
    stl_tbl_lead %>%
      mutate(propBlack = black / totalPop) %>%
      ggplot(aes(x = pctElevated, y = propBlack)) +
        geom_point() +
        geom_smooth()

  # relationship between poverty and lead test results?
    stl_tbl_lead %>%
      mutate(propPvty = povertyTot / totalPop) %>%
      ggplot(aes(x = pctElevated, y = propPvty)) +
        geom_point(method=lm) +
        geom_smooth()

}