Abstract
Citi-Bike is becoming more and more popular in NYC daily public transportation. This project focuses on the distribution of trip duration and see whether most of Citi-Bike trips are lower than 20 minutes, in order to see whether Citibike will be as a solution to travel a short distance, or as a routine commuter program. The study found that the fraction of long(>20min) trips over total number of trips on weekdays is less than the fraction of short( <20min) trips over total number of trips on weekdays.
Introduction
Citi Bike is a privately owned public bicycle sharing system serving New York City and Jersey City, New Jersey. Named after lead sponsor Citigroup, it is operated by Motivate (formerly Alta Bicycle Share), with former Metropolitan Transportation Authority CEO Jay Walder as chief executive. The system's bikes and stations use BIXI-branded technology from PBSC Urban Solutions.This research tries to answer the question of whether there are more long trips of Citi Bike then short trips of it on weekdays.
Data
The data used in this research is retrieved from Citi Bike’s open data. The analysis is based on all the trips
in January 2014. The research try to figure out the riding behavior on weekdays. Thus I transfer the
column “start time”, which is in string format, to column “date” with function “to date time”. Meanwhile, since
only trip duration and weekdays are required for this research, other features are all dropped.
Methodology
Chi-square test is chosen for this research. It is because the research works on two unpaired group - long trips and short trips. At the same time, although the trip duration are in numeric types, I put them into two categories - long trips (>20 minutes) and short trips ( <20 minutes ).