Republican-leaning states tend to have more traffic deaths

Back in 2014, the U.S. Department of Transportation released a report on the (normalized) number of traffic deaths in each U.S. state. As I looked through the list, I noticed an odd correlation between the political leanings of a state and its traffic fatalities.

To confirm this notion, I used box plots to show the distribution of traffic deaths based on how Republican-leaning each state is, where each dot represents a state.

republican-victories-vs-traffic-deaths

In case you’re wondering, Delaware is the Democratic outlier with 1.26 deaths per 100 million miles traveled. Outliers aside, we see an abundantly clear trend: Republican-leaning states tend to have more traffic deaths.

To provide another view, I plotted the same data set as a scatter plot and fit a linear regression below. Each dot represents a state. Again, we see a strong relationship between Republican-leaning states and more traffic deaths.

republican-victories-vs-traffic-deaths-scatter

At this point, I feel obligated to make the caveat that these charts only establish a correlation, and it doesn’t mean that residents of Republican-leaning states experience higher traffic deaths because they tend to vote Republican. However, it sure makes for an interesting statistic to ponder: why would there be a correlation between traffic death rate and tendency to vote Republican?

Thanks to David Fairlie for sharing these interesting statistics on /r/DataIsBeautiful.

Dr. Randy Olson is a Senior Data Scientist at the University of Pennsylvania, where he develops state-of-the-art machine learning algorithms with a focus on biomedical applications.

Posted in data visualization Tagged with: , , ,
  • Heidi Johnson

    Love it. Haven’t seen a box plot since I retired. How about the amount of money spent per mile of highway in Rep. vs. Dem. states? Maybe those conservatives are making the world more dangerous by their anti-spending policies. Too bad they haven’t declared war on infrastructure. ; )

    • HarshTimes

      I think for the GOP it depends on what the money is to be spent towards more so than just being averse to spending.

  • Ryan Kupyn

    If I had to guess, the relative shortcomings of emergency response in more rural (and Republican!) states probably contributes to this. When it takes longer for help to be dispatched, arrive, and take accident victims to a hospital, the likelihood of survival goes down.

    But then again, I just did a quick check, and it looks like there isn’t a super strong relationship between the portion of crashes occurring in rural areas and the fatality rate (r-squared = 0.25).

    If you want a super-deep dive into car-crash data, the California Highway Patrol has information available on each reported car crash in the state available (http://iswitrs.chp.ca.gov/Reports/jsp/RawData.jsp). I used it when trying to find the safest car to buy (end result – larger is better, but the effect of vehicle choice on car crash injury severity is miniscule compared to buckling up).

    In the end (based largely on my experience living in Seattle and LA), I’d suppose the slower average speeds of drivers stuck in giant liberal cities has an effect as well – it’s pretty hard to kill yourself if you’re crawling through traffic or a city center at 10 miles an hour.

  • jasper

    Hi, Edward Tufte has a part of the explanation in https://www.edwardtufte.com/tufte/dapp/

  • Mike

    Liberty is risky.

  • JMS

    This is a light treatment of a lot of data. Rural areas…Roadways…Commuter travel vs public transportation and economic factors.

  • David

    It would be interesting to see the number of accidents in this light. That would help deduce whether the death was caused more by a failure of drivers themselves or that of the post-accident response.

  • sworddance

    My guess is that democratic leaning states tend to do more to help people walk and bike safer.

About this blog

This blog is my labor of love, and I've spent hundreds of hours working on the projects that you'll read about here. Generally, I write about data visualization and machine learning, and sometimes explore out-of-the-box projects at the intersection of the two. I hope you enjoy my projects as much as I have.

If you would like to use one of my graphs on your website or in a publication, please feel free to do so with appropriate attribution, but I would appreciate it if you email me first to let me know.

Archives

Subscribe

Enter your email address to subscribe to this blog and receive notifications of new posts by email.