\documentclass[10pt]{article}
\usepackage{fullpage}
\usepackage{setspace}
\usepackage{parskip}
\usepackage{titlesec}
\usepackage[section]{placeins}
\usepackage{xcolor}
\usepackage{breakcites}
\usepackage{lineno}
\usepackage{hyphenat}
\PassOptionsToPackage{hyphens}{url}
\usepackage[colorlinks = true,
linkcolor = blue,
urlcolor = blue,
citecolor = blue,
anchorcolor = blue]{hyperref}
\usepackage{etoolbox}
\makeatletter
\patchcmd\@combinedblfloats{\box\@outputbox}{\unvbox\@outputbox}{}{%
\errmessage{\noexpand\@combinedblfloats could not be patched}%
}%
\makeatother
\usepackage[round]{natbib}
\let\cite\citep
\renewenvironment{abstract}
{{\bfseries\noindent{\abstractname}\par\nobreak}\footnotesize}
{\bigskip}
\titlespacing{\section}{0pt}{*3}{*1}
\titlespacing{\subsection}{0pt}{*2}{*0.5}
\titlespacing{\subsubsection}{0pt}{*1.5}{0pt}
\usepackage{authblk}
\usepackage{graphicx}
\usepackage[space]{grffile}
\usepackage{latexsym}
\usepackage{textcomp}
\usepackage{longtable}
\usepackage{tabulary}
\usepackage{booktabs,array,multirow}
\usepackage{amsfonts,amsmath,amssymb}
\providecommand\citet{\cite}
\providecommand\citep{\cite}
\providecommand\citealt{\cite}
% You can conditionalize code for latexml or normal latex using this.
\newif\iflatexml\latexmlfalse
\providecommand{\tightlist}{\setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}}%
\AtBeginDocument{\DeclareGraphicsExtensions{.pdf,.PDF,.eps,.EPS,.png,.PNG,.tif,.TIF,.jpg,.JPG,.jpeg,.JPEG}}
\usepackage[utf8]{inputenc}
\usepackage[english]{babel}
\begin{document}
\title{Comparing the proportion of Citi-Bike commuters among different age~}
\author[1]{Mingyi He}%
\affil[1]{New York University}%
\vspace{-1em}
\date{\today}
\begingroup
\let\center\flushleft
\let\endcenter\endflushleft
\maketitle
\endgroup
\sloppy
Reproducible Research: Please check
~\url{https://github.com/Mingyi1995/PUI2018\_mh5172/tree/master/HW8\_mh5172}
\subsection*{}
{\label{443862}}
\subsection*{Abstract}
{\label{443862}}\par\null
The null hypothesis is the proportion of people younger than
30-years-old biking on weekdays' rush-hour is the same or lower than the
proportion of people older than 30-years-old biking on weekdays'
rush-hour, [?] = 0.05. However, the result of z-test suggests that we
cannot reject the null hypothesis.
\par\null\par\null
\subsection*{Introduction}
{\label{976305}}\par\null
Citi Bike is the most wide-spread bike share program in the United
States. It was established in 2013, for now, there are more than 12,000
bikes and 750 stations in Manhattan, Brooklyn, and Queens. My idea is in
the first three months of 2016, as the weather is cold, people not that
young is less likely to ride to work. In my homework 4, I made some
mistakes.~I directly used the absolute value of young and old riders in
weekday and weekends.~Dr. Bianco pointed out that I am supposed to use
the ratio, and the plot should be only two bins: weekdays and
weekends.~I followed her suggestion and modified my project. In this
case,~ Dr.Bianco suggested me to use Chi-Square test or Z-test, I chose
Z-test as I added more data (3 months) and divided them into 14 weeks.
\par\null
\subsection*{Data}
{\label{550013}}\par\null
Download the Citi Bike usage data in January, February and March 2016,
define the threshold of young people is 30-years-old and rush hour is 8,
9, 17 and 18'o clock. I calculated the proportion of Citi Bike usage in
the weekdays' peak time during any time. ~
\par\null\selectlanguage{english}
\begin{figure}[h!]
\begin{center}
\includegraphics[width=0.70\columnwidth]{figures/Screen-Shot-2018-11-04-at-1-21-47-PM/Screen-Shot-2018-11-04-at-1-21-47-PM}
\caption{{The structure of data after been preprocessed
{\label{953528}}%
}}
\end{center}
\end{figure}\selectlanguage{english}
\begin{table}[h!]
\centering
\normalsize\begin{tabulary}{1.0\textwidth}{CCC}
week of year & young proportion & old proportion \\
1 & 0.37 & 0.31 \\
2 & 0.36 & 0.32 \\
3 & 0.39 & 0.4 \\
4 & 0.3 & 0.19 \\
5 & 0.36 & 0.29 \\
6 & 0.39 & 0.36 \\
7 & 0.34 & 0.26 \\
8 & 0.36 & 0.28 \\
9 & 0.37 & 0.31 \\
10 & 0.36 & 0.31 \\
11 & 0.36 & 0.3 \\
12 & 0.36 & 0.32 \\
13 & 0.4 & 0.4 \\
53 & 0.18 & 0.04 \\
\end{tabulary}
\caption{{The distribution of young riding-commuter proportion and old
riding-commuter proportion in different weeks
{\label{347957}}%
}}
\end{table}\par\null
\subsection*{Methodology}
{\label{900211}}\par\null
Employed Z-test to analysis is there a significant difference between
the proportion of young riding-commuters and old riding-commuters. The
result of Z-test is 0.59; this value is smaller than 1.64, which means
we cannot reject the null hypothesis. The proportion of riding-commuters
among young citizens might be smaller than or the same as old. Besides~
Z-test, the Chi-Square test is also feasible in this case.\selectlanguage{english}
\begin{figure}[h!]
\begin{center}
\includegraphics[width=0.70\columnwidth]{figures/bar/bar}
\caption{{Comparing among young people and old people, the proportion of weekdays'
riders in the first 14 weeks of 2016 (the 53rd week is the first week).
{\label{865608}}%
}}
\end{center}
\end{figure}
\par\null
\subsection*{Conclusions}
{\label{141900}}\par\null
In the first three months of 2016, the proportion of people younger than
30-years-old biking on weekdays' rush-hour is the same or lower than the
proportion of people older than 30-years-old biking in the same period,
[?] = 0.05.
\par\null
In this project, the weakness is I didn't do much work on data
wrangling, only dropped those data point without the riders' age.
Moreover, apart from the population of different riders, the trip
duration of each person should also be taken into consideration.~
\selectlanguage{english}
\FloatBarrier
\end{document}