Are People Using Uber as an Alternative to Drinking and Driving?

Could
ridesharing services be saving lives? 

As pressure from taxi unions and DMVs has mounted across the
United States, popular ridesharing services like Uber, Lyft, and
Sidecar have faced bans and setbacks in several cities.
Pittsburgh is one of the most recent places to force
ridesharing services to close up shop. Intrigued by the local
government’s claim that these ridesharing services are detrimental
to the public, Nate Good, a computer scientist, investigated
what kind of societal effect they really have.

Good examined data in Pittsburgh’s sister city, Philadelphia,
because Pittsburgh’s data was not available. His quick and dirty
number crunching compared the DUI rate from January 2004 to January
2013 to the DUI rate from April 2013 (the first time that all
ridesharing services were in effect) to December 2013. He found
that the DUI rate decreased by 11.1 percent in the ridesharing era.
The drop for people under 30 was even more impressive: 18.5
percent. 

As Good notes, correlation does not mean causation and the study
design was far from comprehensive. But it is highly probable that
Uber and its brethren has saved more than a few lives. In May, Uber
published a similar study that examined data in
Seattle:

“We estimate that the entrance of Uber in Seattle caused the
number of arrests for DUI to decrease by more than 10%. These
results are robust and statistically significant. The diagram below
illustrates the “Uber effect” relative to the baseline of
DUIs.”

These results here should be taken with an even bigger grain of
salt. Uber obviously has a significant stake in the outcome so the
potential for bias is high. Perhaps these looks at the data will
encourage others to take a more systematic dive into intuitive
assertion that people will choose a convenient, reasonably priced
alternative to drinking and driving when it is available.