Measuring the impact of re-segregation on Florida elementary schools
Using race, income, and other data to predict the performance of schools in Pinellas County, Florida. Along with a linear regression-driven critique.
linear regression seaborn race census data education
Readings and links
- Failure Factories, series homepage
- Why Pinellas County is the worst place in Florida to be black and go to public school, the first part of the series
- A regression-driven critique from a member of the public, see right-hand column for more critique posts
- Building Failure Factories: How Pinellas County is failing its Black Students, a writeup and series of charts and analyses for a class at Yale by Jaclyn Price
Summary
This chapter is a reproduction of a tiny sliver of the Tampa Bay Times' investigation into the impact of re-segregation in one section of the Florida school system. While the Tampa Bay Times did not publish their regression analysis, it was done as part of the research into school performance.
This chapter also ties into a series of blog posts critical of the investigation, where the author claims that these schools are actually performing as well or better than could be expected.
We'll investigate these claims by performing linear regression with demographics and standardized test data. Beyond technical topics such as coefficients and residuals, this chapter offers fertile ground for discussion of the relationship between social issues, journalism and interpreting statistical analysis.
Notebooks, Assignments, and Walkthroughs
Linear regression on Florida schools, complete walkthrough
A complete walkthrough of combining school-related datasets and researching the relationship between race, free/reduced lunch status, and test performance.
Linear regression on Florida schools, no cleaning
An investigation into the relationship between race, free/reduced lunch status, and test performance.