Insurance redlining -- a complete example



Use the left and right arrow keys to navigate the presentation forward and backward respectively. You can also use the arrows at the bottom right of the screen to navigate with a mouse.

This site is for educational purposes only. This website may contain copyrighted material, the use of which has not been specifically authorized by the copyright holders. The material is made available on this website as a way to advance teaching, and copyright-protected materials are used to the extent necessary to make this class function in a distance learning environment. The Fair Use Copyright Disclaimer is under section 107 of the Copyright Act of 1976, allowance is made for “fair use” for purposes such as criticism, comment, news reporting, teaching, scholarship, education and research.


  • The following topics will be covered in this lecture:
    • Introduction to the data
    • The ecological fallacy
    • Exploratory analysis
    • Model selection
    • Diagnostics
    • Evaluating uncertainty
    • Evaluating the sensitivity of parameter estimates
    • Evaluating predictive power
    • Qualifying our analysis and conclusions
    • A final summary


  • In the following lecture, we will go through a relatively complete example of the process of data analysis, regression, diagnostics, and remediation.

  • Particularly, we will discuss a difficult to analyze question of systematic bias in insurance practices.

  • Insurance, by nature of their business, need to price the cost of covering the risk of damages, based on the probability of these damages.

    • There are many legitimate reasons we can imagine why an insurance company would raise the prices on a driver who frequently violates road rules and is an overly agressive driver;
    • this individual is more likely to cause damages to themsevles or others, and therefore, the price to cover these damages will increase (or insurance will be refused altogether).
  • However, we are also in a society that has historically enforced segregation, unequal rights and unequal access to services.

    • While these were once considered legitimate legal practice, discriminatory business practices are now generally considered immoral and illegal.
    • Moreover, while these direct discriminatory practices have largely ended, they have led to historical and lasting inequality in the communities that have been affected by them.

Introduction – continued

  • We will investigate a complicated question:

    • were insurance companies applying discriminatory business practices on majority non-white neighborhoods in Chicago,
    • or were their practices justifiable based on standard business practices, e.g.,
    • limiting access or raising prices based on justifiable crime statistics, etc?
  • The term “insurance redlining” refers litterally drawing a red line in a map, that excludes certain neighborhoods from services.

  • In the late 1970s, the US Commission on Civil Rights examined charges by several Chicago community organizations that insurance companies were redlining their neighborhoods.

  • Because comprehensive information about individuals being refused homeowners insurance was not available, the number of FAIR plan policies written and renewed in Chicago by zip code for the months of December 1977 through May 1978 was recorded.

  • The FAIR plan was offered by the city of Chicago as a default policy to homeowners who had been rejected by the voluntary market.

  • Information on other variables that might affect insurance writing such as fire and theft rates was also collected at the zip code level.

Chicago (chredlin) dataset