Traffic Crashes Caused by Driving under the Influence adjacent to Colleges/Universities: GIS Analysis and Bayesian Poisson Gamma Modeling
Driving Under the Influence (DUI) is a major public health concern, especially among young drivers. According to the National Highway Traffic Safety Administration (2014), ages 21-24 had the highest percentage of fatal crashes with Blood Alcohol Contents (BACs) of .08 or higher in 2013. At this level judgement and coordination are impaired which are necessary for driving. Since these ages are overrepresented around colleges/universities, there tend to be statistically significant higher rates of DUI crashes in these areas. This study identifies contributing factors for these crashes to be used to find solutions for this problem.
Crash, socio-demographic, roadway traffic, and land-use data were collected from Florida. GIS was applied to find the maximum range adjacent to campuses with higher DUI crash rates. A Bayesian Poisson gamma model was developed to identify contributing factors for these crashes.
The GIS analysis revealed that DUI crash rates caused by young drivers are significantly higher within 2 miles of campuses. The Bayesian Poisson Gamma model identified that locations such as bars, cocktail lounges, and nightclubs land-use areas have significant effects on the number of these crashes. Traffic volume, intersection density, college/university enrollment density, and proportion of white and male students also have significant effects.
Results can be used to create effective policies to reduce DUI involved crashes. For example, police agencies should focus on the areas within 2 miles from campuses to enforce DUIs. School-based education and safety campaigns can be implemented considering the contributing factors in this study.
Learning Areas:Public health or related research
Identify contributing factors for young driver DUI crashes.
Keyword(s): Alcohol Use, Transportation
Qualified on the content I am responsible for because: I have been involved in multiple traffic safety studies focusing on microscopic and macroscopic analyses. One of the main parts in these studies is utilization of different statistical models and other techniques such as data mining, ArcGIS, etc.
Any relevant financial relationships? No
I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.