Voter Lists and Redistricting Simulations for North Carolina and Georgia

10,000 redistricting simulations for North Carolina and Georgia's congressional districts validate Bayesian Improved Surname Geocoding (BISG) methods. The dataset includes voter lists necessary for estimating individual race via BISG, created by John Curiel of MIT. It supports testing the viability of probabilistic versus plurality race assignment methods for redistricting.

Use Cases

• Validating Bayesian Improved Surname Geocoding (BISG) methods based on voter lists and simulation results described.
• Comparing error rates of probabilistic versus plurality racial assignment methods at precinct and district levels as discussed.
• Aiding in the construction of majority-minority districts during the redistricting process based on the described BISG estimates.
• Simulating redistricting scenarios for states like North Carolina and Georgia lacking voter file race data as mentioned.

Strengths

• Includes 10,000 redistricting simulations for validation.
• Compares BISG estimates to actual voter file racial data for two states.
• Created by a researcher at the Massachusetts Institute of Technology.

Limitations

• Row count and file size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

John Curiel, Massachusetts Institute of Technology

Collection Method

Likely compiled from voter lists and used for Bayesian inference simulations.

Geography

North Carolina and Georgia, United States