More granular geographical data has allowed social scientists to probe how residential neighborhoods are formed and how they influence attitudes and behavior. To facilitate such studies, we develop a survey tool that allows respondents to draw their neighborhoods on a map. We propose a hierarchical Bayesian model that can be used to analyze which factors shape their neighborhoods. We have conducted a survey of registered voters in Miami, New York City, and Phoenix, and find that across these cities, voters are more likely to include same-race and co-partisan census blocks into their neighborhoods. We also show that our model provides more accurate out-of-sample predictions than the standard distance-based measures of neighborhoods.
This is joint work with Jacob R. Brown and Kosuke Imai.