The New York Times, in what seems like a continuing series on NYC transportation, has an article about a decline in subway ridership. The article points out declines that were to be expected such as in the financial district or Midtown as well as expected increases like along J, which shares a route with the M and Z which are facing service cuts. It will be interesting to see how these findings impact the expected service cuts.
Another area with expected results was a massive drop off at the moribund Mets’ stop and a below average drop at the World Champion Yankees stop. However, the Mets–unlike the Yankees–have a convenient commuter rail stop. Perhaps that explains the drop more than the team’s performance.
The data is based on subway entrances, but I think it would be telling to see where people are exiting the trains. Commuting habits shouldn’t be expected to be symmetric as people are more likely to walk home from their office than to the office. Plus people might go to dinner or a bar after work which pulls them to a nearby, but different station. And let’s not forget all the people stuck in the office late who take a cab home.
It would also be interesting to try to figure out where people were starting and where they ended. I’m not sure if this can be tracked, but it would be great to see what residential neighborhoods are tied to which business neighborhoods.
The article has a nice accompanying interactive map which helps visualize ridership.
I would be interested in how the numbers were computed. Were they simple rates or was a regression used? The data are available if anyone wants to play with them some more.
Jared Lander is the Chief Data Scientist of Lander Analytics a New York data science firm, Adjunct Professor at Columbia University, Organizer of the New York Open Statistical Programming meetup and the New York and Washington DC R Conferences and author of R for Everyone.