Citi-bike project conclusion

Yuan Shi, Yao Wang

  • Abstract (short summary of the idea, the analysis, the result)

Using 2015 Jan Citi bike data, compare age distribution of male users and female users, compare age distribution of daytime and nighttime users, compare age distribution of all the users with normal distribution. The analysis involved KS Test, Pearson's Test, Spearman's Test, AD Test. The results are, age distributions of male and female users are different, of nighttime and daytime are different, all the users' age distribution is not normal distribution.

  • Data

2015 January Citi Bike Data,

The Citi Bike data contains related information of all Citi Bike used in 2015 Jan, including trip duration, start time, stop time, start station id, start station name, start station latitude, start station longitude, end station id, end station name, end station latitude, end station longitude, bike id, user type , birth year, gender.
The purpose of this project is to know the age distribution of Citi Bike users, relationship of age with gender, relationship of age with using time (assuming start time 
Double click  todistinguish daytime 6am-6pm and nighttime 6pm-6am). So the used information from Citi Bike document is,  start time, birth year and gender. 

  • Analysis

Compare age distribution of male and female, use KS TEST ,Pearson's Test and Spearman's Test to judge if normalized cumulative functions are of same distribution.