Visualizing margins of error in the ACS

Analyzing US Census Data in R

Kyle Walker

Instructor

Visualizing uncertainty

Common approach: error bar plots

Example error bar plot

Margin of error plots in ggplot2

In ggplot2: geom_errorbar() and geom_errorbarh()

library(tidycensus)
library(tidyverse)

wyoming_age <- get_acs(geography = "county", 
                       variables = c(medianage = "B01002_001"), 
                       state = "WY")  

ggplot(wyoming_age, aes(x = estimate, y = NAME)) + 
  geom_errorbarh(aes(xmin = estimate - moe, 
                     xmax = estimate + moe)) + 
  geom_point()

unformatted margin of error plot

Formatting margin of error plots

wyoming_age2 <- wyoming_age %>%
  mutate(NAME = str_replace(NAME, " County, Wyoming", ""))

ggplot(wyoming_age2, 
       aes(x = estimate, 
           y = reorder(NAME, estimate))) + 
  geom_errorbarh(aes(xmin = estimate - moe, 
                     xmax = estimate + moe)) + 
  geom_point(size = 3, color = "darkgreen") + 
  theme_grey(base_size = 14) + 
  labs(title = "Median age, counties in Wyoming", 
       subtitle = "2012-2016 American Community Survey",
       x = "ACS estimate (bars represent margins of error)", 
       y = "")

formatted margin of error plot

Let's practice!

Analyzing US Census Data in R