Student Name: Xinge Zhong(viola), Github account: xingezhong, NetID: xz1809

Some notes outlining progress on a question concerning Gibbs’ Paradox. Not everything will be totally cogent / concise, as they are working notes. Project supervised by A. Grosberg at NYU, Autumn 2013.

INTORDUCTION This is a article about CitiBike Sharing Project in PUI2016 class. The Report includes four parts Abstract, Data, Analysis and Result, which will be described in the following parts.

This study aims to find out whether or not young people ride bikes on weekends more often than that of middle-aged people. The analysis performs a hypothesis test (Z-test) to compare the ratio of the number of young people using citi bikes on weekends over weekdays to that of mid-age people. The result shows that under 5% significance level, the ratio of the number of young people biking on weekends over week days(7 days) is greater than the counterpart middle-aged people.

ABSTRACT The objective of this analysis was to perform a data-driven analysis of CitiBike trip data in New York City using statistical testing in python. Using CitiBike data from June 2016, the relationship between rider age and trip duration was explored. Specifically, the ratio of long distance trips to all distance trips in young riders was compared to that of all riders. Younger riders typically have more energy and strength, which translates into the ability to ride farther distances compared to all riders. The result of this analysis did not result in a significant difference between young riders and all riders, and therefore the null hypothesis could not be rejected. DATA The data for this analysis was obtained from the CUSP Data Facility at New York University. The data was subset to only fields needed to calculate rider trip distance: Start Station Latitude, Start Station Longitude, End Station Latitude, End Station Longitude, and rider birth year. Next, geopy was used to calculate trip distance in miles between the stations. The data wrangling process is detailed in the linked ipython notebook. ANALYSIS Through preliminary data inspection, the team took interest in long-distance trip in CitiBike riders. The team first defined null and alternative hypotheses: Null Hypothesis Long-distance trip ratio in young bikers is less than or equal to long-distance trip ratio in all bikers. $$H_0: Ly/Ay - L/A <= 0$$ Alternative Hypothesis Long-distance trip ratio in young bikers is less than or equal to long-distance trip ratio in all bikers. $$H_a: Ly/Ay - L/A > 0$$ significance level: $$\alpha = 0.05$$ Young riders were defined as millennials born after 1980, and long distance trips referred to trips greater than three miles from start to end station. In the exploratory phase of the analysis, the team reviewed the distribution of CitiBike ridership by birth year (Figure 1). The team then looked at the data pertaining to only long trips greater than three miles in distance for both age groups (Figure 2). The ratio of long trips for all riders was also explored, as shown in Figures 3 and 4. After the exploratory phase, the team began statistical testing. A Z-test was decided upon to test the hypothesis after peer review, and all riders were defined to be the population while millennial riders were defined as the sample to be tested. The ratios of each subgroup defined in the hypothesis were calculated and then tested. RESULTS Looking back at the data, although a young riders have a larger percentage of total trips (Figure 1), younger riders have a relatively small long-distance trip ratio (Figure 2). Therefore, when the Z-test was performed, our p-value indicated that the null hypothesis could not be rejected at a 0.95 significance level. The results of this data analysis reveal that millenial CitiBike riders do not have a significantly higher ratio of long distance trips, and therefore trip distance is not dictated by rider age. Link to ipython notebook on GitHub: https://github.com/nmonarizqa/PUI2016_nm2773/tree/master/HW6_nm2773/HW6_Assignment2.ipynb

These are some ideas stimulated by my research; I write them to make sure I think about / understand certain questions. Some sections will be quite rough / unintelligible.

Author: Le Xu BEST TIME TO DRIVE A CAB? WHEN ARE THE LONGER TRIPS AND HIGHER AVERAGE FARES LIKELY TO HAPPEN? Problem Description: It is generally known that: Fridays’ and Saturdays’ nights are the busiest time period during the week, or bad weather could also help to drive up taxi demands. After the CUSP hack-day working on NYC Taxi dataset, I would love to further study the taxi fares by analyzing with the taxi trip occurring time and the daily weather. In my data analysis, I will answer questions like: What time of the day has better chance of longer trips or higher average trip fare? How bad weather (rain/snow) could affect taxi ridership, etc. Data: (ready for analysis) Data Taxi trip data _Source: NYC Taxi & Limousine Commission - NYC.gov_ Since there will be time series analysis, the taxi data from NYC.gov has included the time of the trip occurring, both the pick-up time and drop-off time, and the total fare as well as the total tip amount. The anticipated data processing will mainly include: binning the timestamps, to discover the trend/periodicity of the taxi income during the day/week/month. Daily Central Park weather data _Source: National Climatic Data Center_ https://www.ncdc.noaa.gov/cdo-web/datasets/GHCND/stations/GHCND:USW00094728/detail This dataset could give me the weather data that I need. *Since the size of the taxi data is rather huge, so I might consider take a subset of the dataset, however I am not sure currently. Analysis Plan: Idea 1: Night has more people go out/dine out and trains are getting slower or less, so night has more long trips than the day. NULL HYPOTHESIS: THE RATIO OF NUMBERS OF TAXI LONGER TRIPS OVER TOTAL NUMBERS OF TRIPS OCCURRED DURING THE DAYTIME IS SAME OR HIGHER THAN THE RATIO OF NUMBERS OF TAXI LONGER TRIP OVER TOTAL NUMBERS OF TRIPS OCCURRED DURING THE NIGHTTIME. Range of hours for this analysis. Day time (from 6:00 to 18:00) Night time (from 18:00 to 6:00) $$H0 : {Total Day Trip}\geq {Total Night Trips} $$ $$H1 : {Total Day Trip}\< {Total Night Trips} $$ I will use a significance level $$\alpha=0.05$$ I will probably use one month data in the winter and one month in the summer time. Idea 2: How the weather would affect the taxi demand? Rainy day could either drive up demands because people might not have umbrellas, or idle the demand because less people want to go out because of the rain. For the taxi rides with weather condition analysis, extreme events will be identified through outlier detection via thresholds. Clustering/Correlation Analysis could be performed in order to examine the relationship between taxi demands and weather. Analysis Tools: Pandas, matplotlib References: Analyzing 1.1 Billion NYC Taxi and Uber Trips, with a Vengeance - Todd W. Schneider http://toddwschneider.com/posts/analyzing-1-1-billion-nyc-taxi-and-uber-trips-with-a-vengeance/ Visual Exploration of Big Spatio-Temporal Urban Data: A Study of New York City Taxi Trips - Nivan Ferreira, Jorge Poco, Huy T. Vo, Juliana Freire, and Claudio T. Silva link_text NYC Taxi Trip and Fare Data Analytics using BigData - Umang Patel # Deliverable: Idea 1: The result of the statistical analysis, with at least two figures to support. Idea 2: The result of the Clustering/Correlation Analysis.

ABSTRACT This project investigated CitiBike rider and membership usage data, seeking to determine whether CitiBike sells more 24-Hour passes over the weekend or weekdays during quarter 2, April to June, of 2016. The statistical test used in this investigation was the _T-TEST_, which yielded a t-test statistic of 5.5 and p-value of 6.4 x 10-6. Accordingly, the null hypothesis was rejected and the alternative hypothesis was accepted: concluding that more 24-Hour passes were indeed purchased over the weekend, Saturday - Sunday, than during weekdays in April to June 2016. This analysis can be seen on Github: https://github.com/jvani/PUI2016_jmv423/blob/master/HW6_jmv423/Assignment2_jmv423.ipynb

AbstractUrban environments are growing more and more complex by the day. The emotional feeling of safety for a person interacting with these environments depends on a multitude of elements. Some of these elements are tangible/measurable whereas some of them are intangible. Social Science literature has shown a strong connection between the visual appearance of a city and its streets with the behavior and health of its citizens[1]. When the appearance of a neighborhood is considered with its impact on the health and behavior of the individuals that inhibit them, many aspects can be considered in this regard.Visual perception is one of the major elements that would help us understand actual safety of a neighborhood. MIT Media Lab has tried to quantify safety based on the visual perception of the neighborhoods. Beyond visual perception, there are characteristics of the neighborhood which do not get captured in an image which is frozen in time.  In this study we are trying to explore different physical, socio-economic and incidental factors to see how closely they relate with the visual perception of safety. For example, taking into consideration a tourist coming entering a city for the first time. According to this tourist, the city may actually be perceived to be the best in the world and this perception can be skewed when considering safety in various areas around the city. This is because cities are usually heterogeneous in nature, and often unequal with respect to safety, demographics, cleanliness of the neighborhoods, the beauty of their architecture and many other evaluative dimensions. These aspects of the city although not saying much contribute highly to the perceived safety of the city as a whole or even as parts. This statement and example mentioned above creates some questions than need to be answered with respect to safety and its perception:What does the perception of safety tell us about different streets, neighborhoods or cities? Does the quality of the surroundings depend on the architecture or the width of the street or the amount of greenery? Is it possible that there is there another, unknown and semi-subconscious factor at play on our perceptions of safety?

Author: Chunqing Xu, Le Xu, Jianghao Zhu * Abstract This is analysis on citibike data. The idea is to see if age will affect the behavior of biking. The idea in this analysis is if younger woman is more likely than younger man choose riding a bike. Followed by data analysis and result.

Profile - Achilles_SaxbyGitHub - achillessaxbyNYU - aes807

ABSTRACT The Citi Bike bike-share system in New York City has been aggressively expanding its coverage in 2016. Bike-share systems work by building clusters of bicycle docks within its 'service area'. This cluster has a border outside of which there are no stations. To understand where pent-up demand might still exist, we investigated whether there was increased usage of bike share stations along the border in Northern Manhattan as of June 2016. We selected 10 stations roughly along 84th Street. We compared average usage at these stations with 20 stations directly south of this border, what we call the 'non-boundary' stations. We hypothesize that boundary stations will see higher average usage than non-boundary stations since anyone living north of the border will likely use and drop off bikes along the system's edge.

Double click to add an Abstract

Abstract

Abstract:In this projected we intended to find out if older Citi-Bike riders take longer duration trips than younger riders. Our statistical comparison of means indicates that that is indeed the case.

Github: PatrickGitunduNYUID: pgm293Problem Description: In public safety, response delays (even to the minute) to crimes as they happen could mean the difference between life and death. Despite a decline in the number of “crime in progress” calls over the last three years, NYPD response times to crimes in progress and non-critical calls are all up, according to the 2016 Mayor’s Management Report released in September of this year. To get a grasp of the dynamics in response times could be invaluable. The NYPD releases a data set of the major felonies committed in the city per precinct as well as the response times for those crimes.Goals:By analyzing this data set of crimes by precinct and response time, can we :-1. Predict future response times by the precinct and crime. What will be the response time to crimes in the future?2. Identify trends, events or periodicity with regards to the response time?3. Identify the ‘slowest’ precincts?4. Spatially visualize the response times for crimes in progress using a ‘responsiveness’ scale for each precinct (zip code might be possible as well)?Data: The data to be used will be the NYPD public Indicators dataset hosted on New York City open data platform. The dataset contains response times for crimes in progress. The crimes recorded are split according to the 7 major felonies as well as by precinct.Analysis: I will look to predict future response times using regression. I will also carry out several time-series analyses with the data. I will look for trends by smoothing, look for any events through thresholds, lastly I will search for periodicity using ARMA. In addition to the above I will also look to use spatial autocorrelation through LISA to create a spatial ‘heat map’ of the average response times as seen geographically by precinct service area boundaries and zip code. This heat map will show the responsiveness of precincts on a scale from 1 to 10.Deliverable: As a deliverable, I would like to come up with a report showing my statistical and spatial conclusions about the response times and crimes as handled by precinct and time. This could be useful in identifying slower precincts and helping the city administration to better allocate resources towards bringing the response time to crimes in progress down.References: Anthony Shorris, Mindy Tarlow. The Mayor’s Management Report – September 2016.