Traffic safety has become an emerging issue in the city of New York since the pandemic. This project aims to use causal inference methods to investigate how traffic safety countermeasures (including adding more bike lanes) that have been deployed by the city affect traffic fatalities.

M.S. are welcome to register research credits throughout the semesters. The student involved in this project will conduct a comprehensive literature review at the intersection of traffic safety and causal inference and develop machine learning models. Students with good computer and coding skills are preferred. Skill requirements are:

  1. Explore open datasets and extract useful information, including NYC Open, Fatality Analysis Reporting System (FARS) from NHTSA (https://www.nhtsa.gov/research-data/fatality-analysis-reporting-system-fars), and Highway Performance Management System (https://www.fhwa.dot.gov/policyinformation/hpms.cfm).
  2. Familiar with deep learning or/and causal inference models.
  3. Familiar with R and Python. Generating figures, graphs, tables, or statistical models to present results.

This is an UNPAID research project.

Faculty Advisor

Project Timeline

  • Earliest starting date: 9/1/21
  • End date: 12/31/21
  • Number of hours per week of research expected during Summer 2022: ~20

Candidate requirements

  • Skill sets: programming, data processing and visualization, literature review
  • Student eligibility: freshman, sophomore, junior, senior, master’s
  • International students on F1 or J1 visa: eligible
  • Academic Credit Possible: Yes