Models Make a Difference: Predicting Geospatial Teen Crash Frequency

According to the National Highway Traffic Safety Administration (NHTSA), in 2019 almost 2,400 teens in the United States aged 13–19 were killed in motor vehicle crashes. Per the Insurance Institute for Highway Safety (IIHS), crash rates per mile driven for teen drivers are nearly four times those of drivers 20 years and older. New Mineta Transportation Institute (MTI) research, Modeling and Predicting Geospatial Teen Crash Frequency, 1) evaluates the effect of road network, demographic, and land use characteristics on road crashes involving teen drivers, and, 2) develops and compares the predictability of local and global regression models in estimating teen crash frequency.

The influence of location-specific indicators (e.g., rural/urban, school vicinity, etc.) on teen crash frequency is difficult to capture from typical safety performance functions, and global regression models may not give accurate estimates at certain locations. Fortunately, Geographic Information System (GIS)-based methods like geographically weighted regression (GWR) can help generate localized safety performance functions (SPFs) by capturing the spatial variations in explanatory variables and accurately computing teen crash frequency.

The study’s main findings include:

• The relationship between teen crash frequency and selected road, demographic, and land use characteristics are complex and vary by geographic location.
• Daily traffic volumes, light commercial (constrained to community-based services such as fast-food centers, commercial stores, service stations, etc.), and light industrial land (light manufacturing-based industries and warehouse-based land use parcels) increase teen crash frequency.

“Based on our research, a geographically weighted negative binomial regression model is a promising method for understanding teen crash frequency,” explain the study’s authors. “Looking at the different variables enables us to understand where we need to focus our policy and education efforts in order to reduce teen crash frequency.”

This research can be used to understand the relative contributions of different variables on teen crash frequency, thus enabling stakeholders to better understand and adopt  effective solutions–—including changes in education, policies, and legislation—for preventing teen crashes. Further research and development of effective teen driver education and enforcement programs can make the roads safer for teens and everyone. Additionally, this method is transferable and can be applied to similar traffic safety and crash prevention issues.

ABOUT THE MINETA TRANSPORTATION INSTITUTE

At the Mineta Transportation Institute (MTI) at San Jose State University (SJSU) our mission is to increase mobility for all by improving the safety, efficiency, accessibility, and convenience of our nations’ transportation system. Through research, education, workforce development and technology transfer, we help create a connected world. Founded in 1991, MTI is funded through the US Departments of Transportation and Homeland Security, the California Department of Transportation, and public and private grants, including those made available by the Road Repair and Accountability Act of 2017 (SB1). MTI is affiliated with SJSU’s Lucas College and Graduate School of Business.

ABOUT THE AUTHORS
Dr. Sarvani Duvvuri received his Ph.D. in Infrastructure and Environmental Systems (INES) from the University of North Carolina at Charlotte, NC. He is a Postdoctoral Researcher with the IDEAS Center. His current research interests include traffic safety, traffic flow modeling and simulation, ITS, connected and automated vehicles, and spatial modeling. Dr. Srinivas S. Pulugurtha, P.E., F.ASCE is currently working as a Professor and Research Director of the Department of Civil and Environmental Engineering at the University of North Carolina at Charlotte. He is also the Director of the IDEAS Center. Dr. Sonu Mathew received her Ph.D. in Infrastructure and Environmental Systems (INES) from the University of North Carolina at Charlotte, NC. Her current research interests include traffic operations and safety, traffic simulation, and connected and automated vehicles.

Media Contact: