Several news outlets have reported on the relationship between the racial composition of US counties and their pollution levels as measured by the Environmental Protection Agency. Basic analysis including maps and summary statistics indicate that counties with unsatisfactorily high pollution levels (as determined by the EPA) tend to be less White. Can this relationship between race and pollution be quantified further by statistical analysis?
In this project I will use regression analysis and Chi-squared testing to assess the dependency relationship between race and pollution in US counties monitored by the EPA. I hope this work can extend other prior analysis and provide more statistical certainty to claims of environmental racism.