Telling-Stories-with-Data.toc

\contentsline {fm}{Preface}{ix}{chapter*.1}%
\contentsline {chapter}{Preface}{ix}{chapter*.1}%
\contentsline {section}{Audience and assumed background}{x}{section*.2}%
\contentsline {section}{Structure and content}{x}{section*.3}%
\contentsline {section}{Pedagogy and key features}{xii}{section*.4}%
\contentsline {section}{Software information and conventions}{xiii}{section*.5}%
\contentsline {section}{About the author}{xiv}{section*.6}%
\contentsline {section}{Acknowledgments}{xiv}{section*.7}%
\contentsline {part}{I\hspace {1em}Foundations}{1}{part.1}%
\contentsline {chapter}{\numberline {1}Telling stories with data}{3}{chapter.1}%
\contentsline {section}{\numberline {1.1}On telling stories}{3}{section.1.1}%
\contentsline {section}{\numberline {1.2}Workflow components}{4}{section.1.2}%
\contentsline {section}{\numberline {1.3}Telling stories with data}{6}{section.1.3}%
\contentsline {section}{\numberline {1.4}How do our worlds become data?}{11}{section.1.4}%
\contentsline {section}{\numberline {1.5}What is data science and how should we use it to learn about the world?}{12}{section.1.5}%
\contentsline {section}{\numberline {1.6}Exercises}{14}{section.1.6}%
\contentsline {subsection}{Questions}{14}{section*.10}%
\contentsline {subsection}{Tutorial}{15}{section*.11}%
\contentsline {chapter}{\numberline {2}Drinking from a fire hose}{17}{chapter.2}%
\contentsline {section}{\numberline {2.1}Hello, World!}{18}{section.2.1}%
\contentsline {section}{\numberline {2.2}Australian elections}{19}{section.2.2}%
\contentsline {subsection}{\numberline {2.2.1}Plan}{19}{subsection.2.2.1}%
\contentsline {subsection}{\numberline {2.2.2}Simulate}{19}{subsection.2.2.2}%
\contentsline {subsection}{\numberline {2.2.3}Acquire}{23}{subsection.2.2.3}%
\contentsline {subsection}{\numberline {2.2.4}Explore}{28}{subsection.2.2.4}%
\contentsline {subsection}{\numberline {2.2.5}Share}{29}{subsection.2.2.5}%
\contentsline {section}{\numberline {2.3}Toronto's unhoused population}{30}{section.2.3}%
\contentsline {subsection}{\numberline {2.3.1}Plan}{30}{subsection.2.3.1}%
\contentsline {subsection}{\numberline {2.3.2}Simulate}{31}{subsection.2.3.2}%
\contentsline {subsection}{\numberline {2.3.3}Acquire}{33}{subsection.2.3.3}%
\contentsline {subsection}{\numberline {2.3.4}Explore}{34}{subsection.2.3.4}%
\contentsline {subsection}{\numberline {2.3.5}Share}{36}{subsection.2.3.5}%
\contentsline {section}{\numberline {2.4}Neonatal mortality}{37}{section.2.4}%
\contentsline {subsection}{\numberline {2.4.1}Plan}{37}{subsection.2.4.1}%
\contentsline {subsection}{\numberline {2.4.2}Simulate}{37}{subsection.2.4.2}%
\contentsline {subsection}{\numberline {2.4.3}Acquire}{41}{subsection.2.4.3}%
\contentsline {subsection}{\numberline {2.4.4}Explore}{43}{subsection.2.4.4}%
\contentsline {subsection}{\numberline {2.4.5}Share}{44}{subsection.2.4.5}%
\contentsline {section}{\numberline {2.5}Concluding remarks}{45}{section.2.5}%
\contentsline {section}{\numberline {2.6}Exercises}{45}{section.2.6}%
\contentsline {subsection}{Scales}{45}{section*.20}%
\contentsline {subsection}{Questions}{46}{section*.21}%
\contentsline {subsection}{Tutorial}{47}{section*.22}%
\contentsline {chapter}{\numberline {3}Reproducible workflows}{49}{chapter.3}%
\contentsline {section}{\numberline {3.1}Introduction}{50}{section.3.1}%
\contentsline {section}{\numberline {3.2}Quarto}{53}{section.3.2}%
\contentsline {subsection}{\numberline {3.2.1}Getting started}{53}{subsection.3.2.1}%
\contentsline {subsection}{\numberline {3.2.2}Top matter}{54}{subsection.3.2.2}%
\contentsline {subsection}{\numberline {3.2.3}Essential commands}{55}{subsection.3.2.3}%
\contentsline {subsection}{\numberline {3.2.4}R chunks}{56}{subsection.3.2.4}%
\contentsline {subsection}{\numberline {3.2.5}Equations}{58}{subsection.3.2.5}%
\contentsline {subsection}{\numberline {3.2.6}Cross-references}{60}{subsection.3.2.6}%
\contentsline {section}{\numberline {3.3}R Projects and file structure}{62}{section.3.3}%
\contentsline {section}{\numberline {3.4}Version control}{64}{section.3.4}%
\contentsline {subsection}{\numberline {3.4.1}Git}{65}{subsection.3.4.1}%
\contentsline {subsection}{\numberline {3.4.2}GitHub}{66}{subsection.3.4.2}%
\contentsline {section}{\numberline {3.5}Using R in practice}{69}{section.3.5}%
\contentsline {subsection}{\numberline {3.5.1}Dealing with errors}{69}{subsection.3.5.1}%
\contentsline {subsection}{\numberline {3.5.2}Reproducible examples}{70}{subsection.3.5.2}%
\contentsline {subsection}{\numberline {3.5.3}Mentality}{71}{subsection.3.5.3}%
\contentsline {subsection}{\numberline {3.5.4}Code comments and style}{72}{subsection.3.5.4}%
\contentsline {subsection}{\numberline {3.5.5}Tests}{73}{subsection.3.5.5}%
\contentsline {section}{\numberline {3.6}Efficiency}{73}{section.3.6}%
\contentsline {subsection}{\numberline {3.6.1}Sharing a code environment}{74}{subsection.3.6.1}%
\contentsline {subsection}{\numberline {3.6.2}Code linting and styling}{75}{subsection.3.6.2}%
\contentsline {subsection}{\numberline {3.6.3}Code review}{76}{subsection.3.6.3}%
\contentsline {subsection}{\numberline {3.6.4}Code refactoring}{77}{subsection.3.6.4}%
\contentsline {subsection}{\numberline {3.6.5}Parallel processing}{78}{subsection.3.6.5}%
\contentsline {section}{\numberline {3.7}Concluding remarks}{80}{section.3.7}%
\contentsline {section}{\numberline {3.8}Exercises}{80}{section.3.8}%
\contentsline {subsection}{Scales}{80}{section*.29}%
\contentsline {subsection}{Questions}{81}{section*.30}%
\contentsline {subsection}{Tutorial}{82}{section*.31}%
\contentsline {subsection}{Paper}{82}{section*.32}%
\contentsline {part}{II\hspace {1em}Communication}{83}{part.2}%
\contentsline {chapter}{\numberline {4}Writing research}{85}{chapter.4}%
\contentsline {section}{\numberline {4.1}Introduction}{87}{section.4.1}%
\contentsline {section}{\numberline {4.2}Writing}{87}{section.4.2}%
\contentsline {section}{\numberline {4.3}Asking questions}{89}{section.4.3}%
\contentsline {subsection}{\numberline {4.3.1}Data-first}{90}{subsection.4.3.1}%
\contentsline {subsection}{\numberline {4.3.2}Question-first}{91}{subsection.4.3.2}%
\contentsline {section}{\numberline {4.4}Answering questions}{92}{section.4.4}%
\contentsline {section}{\numberline {4.5}Components of a paper}{94}{section.4.5}%
\contentsline {subsection}{\numberline {4.5.1}Title}{95}{subsection.4.5.1}%
\contentsline {subsection}{\numberline {4.5.2}Abstract}{96}{subsection.4.5.2}%
\contentsline {subsection}{\numberline {4.5.3}Introduction}{99}{subsection.4.5.3}%
\contentsline {subsection}{\numberline {4.5.4}Data}{100}{subsection.4.5.4}%
\contentsline {subsection}{\numberline {4.5.5}Model}{101}{subsection.4.5.5}%
\contentsline {subsection}{\numberline {4.5.6}Results}{103}{subsection.4.5.6}%
\contentsline {subsection}{\numberline {4.5.7}Discussion}{103}{subsection.4.5.7}%
\contentsline {subsection}{\numberline {4.5.8}Brevity, typos, and grammar}{103}{subsection.4.5.8}%
\contentsline {subsection}{\numberline {4.5.9}Rules}{104}{subsection.4.5.9}%
\contentsline {section}{\numberline {4.6}Exercises}{105}{section.4.6}%
\contentsline {subsection}{Scales}{105}{section*.34}%
\contentsline {subsection}{Questions}{105}{section*.35}%
\contentsline {subsection}{Tutorial}{106}{section*.36}%
\contentsline {chapter}{\numberline {5}Static communication}{109}{chapter.5}%
\contentsline {section}{\numberline {5.1}Introduction}{110}{section.5.1}%
\contentsline {section}{\numberline {5.2}Graphs}{111}{section.5.2}%
\contentsline {subsection}{\numberline {5.2.1}Bar charts}{115}{subsection.5.2.1}%
\contentsline {subsubsection}{\numberline {5.2.1.1}Themes}{117}{subsubsection.5.2.1.1}%
\contentsline {subsubsection}{\numberline {5.2.1.2}Facets}{119}{subsubsection.5.2.1.2}%
\contentsline {subsubsection}{\numberline {5.2.1.3}Colors}{121}{subsubsection.5.2.1.3}%
\contentsline {subsection}{\numberline {5.2.2}Scatterplots}{123}{subsection.5.2.2}%
\contentsline {subsection}{\numberline {5.2.3}Line plots}{128}{subsection.5.2.3}%
\contentsline {subsection}{\numberline {5.2.4}Histograms}{131}{subsection.5.2.4}%
\contentsline {subsection}{\numberline {5.2.5}Boxplots}{136}{subsection.5.2.5}%
\contentsline {section}{\numberline {5.3}Tables}{138}{section.5.3}%
\contentsline {subsection}{\numberline {5.3.1}Showing part of a dataset}{139}{subsection.5.3.1}%
\contentsline {subsection}{\numberline {5.3.2}Improving the formatting}{140}{subsection.5.3.2}%
\contentsline {subsection}{\numberline {5.3.3}Communicating summary statistics}{141}{subsection.5.3.3}%
\contentsline {subsection}{\numberline {5.3.4}Display regression results}{143}{subsection.5.3.4}%
\contentsline {section}{\numberline {5.4}Maps}{145}{section.5.4}%
\contentsline {subsection}{\numberline {5.4.1}Australian polling places}{146}{subsection.5.4.1}%
\contentsline {subsection}{\numberline {5.4.2}United States military bases}{149}{subsection.5.4.2}%
\contentsline {subsection}{\numberline {5.4.3}Geocoding}{150}{subsection.5.4.3}%
\contentsline {section}{\numberline {5.5}Concluding remarks}{154}{section.5.5}%
\contentsline {section}{\numberline {5.6}Exercises}{154}{section.5.6}%
\contentsline {subsection}{Scales}{154}{section*.74}%
\contentsline {subsection}{Questions}{154}{section*.75}%
\contentsline {subsection}{Tutorial}{156}{section*.76}%
\contentsline {subsection}{Paper}{156}{section*.77}%
\contentsline {part}{III\hspace {1em}Acquisition}{157}{part.3}%
\contentsline {chapter}{\numberline {6}Farm data}{159}{chapter.6}%
\contentsline {section}{\numberline {6.1}Introduction}{160}{section.6.1}%
\contentsline {section}{\numberline {6.2}Measurement}{162}{section.6.2}%
\contentsline {subsection}{\numberline {6.2.1}Properties of measurements}{164}{subsection.6.2.1}%
\contentsline {subsection}{\numberline {6.2.2}Measurement error}{165}{subsection.6.2.2}%
\contentsline {subsection}{\numberline {6.2.3}Missing data}{167}{subsection.6.2.3}%
\contentsline {section}{\numberline {6.3}Censuses and other government data}{168}{section.6.3}%
\contentsline {subsection}{\numberline {6.3.1}Canada}{170}{subsection.6.3.1}%
\contentsline {subsection}{\numberline {6.3.2}United States}{172}{subsection.6.3.2}%
\contentsline {subsubsection}{\numberline {6.3.2.1}Census}{172}{subsubsection.6.3.2.1}%
\contentsline {subsubsection}{\numberline {6.3.2.2}American Community Survey}{173}{subsubsection.6.3.2.2}%
\contentsline {section}{\numberline {6.4}Sampling essentials}{178}{section.6.4}%
\contentsline {subsection}{\numberline {6.4.1}Sampling in Dublin and Reading}{180}{subsection.6.4.1}%
\contentsline {subsubsection}{\numberline {6.4.1.1}Survey of Dublin in 1798}{180}{subsubsection.6.4.1.1}%
\contentsline {subsubsection}{\numberline {6.4.1.2}Survey of working-class households in Reading in 1912}{181}{subsubsection.6.4.1.2}%
\contentsline {subsection}{\numberline {6.4.2}Probabilistic sampling}{182}{subsection.6.4.2}%
\contentsline {subsubsection}{\numberline {6.4.2.1}Inference for probability samples}{187}{subsubsection.6.4.2.1}%
\contentsline {subsection}{\numberline {6.4.3}Non-probability samples}{191}{subsection.6.4.3}%
\contentsline {section}{\numberline {6.5}Exercises}{193}{section.6.5}%
\contentsline {subsection}{Scales}{193}{section*.86}%
\contentsline {subsection}{Questions}{193}{section*.87}%
\contentsline {subsection}{Tutorial}{194}{section*.88}%
\contentsline {chapter}{\numberline {7}Gather data}{195}{chapter.7}%
\contentsline {section}{\numberline {7.1}Introduction}{196}{section.7.1}%
\contentsline {section}{\numberline {7.2}APIs}{197}{section.7.2}%
\contentsline {subsection}{\numberline {7.2.1}arXiv, NASA, and Dataverse}{198}{subsection.7.2.1}%
\contentsline {subsubsection}{\numberline {7.2.1.1}arXiv}{198}{subsubsection.7.2.1.1}%
\contentsline {subsubsection}{\numberline {7.2.1.2}NASA Astronomy Picture of the Day}{199}{subsubsection.7.2.1.2}%
\contentsline {subsubsection}{\numberline {7.2.1.3}Dataverse}{200}{subsubsection.7.2.1.3}%
\contentsline {subsection}{\numberline {7.2.2}Spotify}{200}{subsection.7.2.2}%
\contentsline {section}{\numberline {7.3}Web scraping}{205}{section.7.3}%
\contentsline {subsection}{\numberline {7.3.1}Principles}{205}{subsection.7.3.1}%
\contentsline {subsection}{\numberline {7.3.2}HTML/CSS essentials}{207}{subsection.7.3.2}%
\contentsline {subsection}{\numberline {7.3.3}Book information}{208}{subsection.7.3.3}%
\contentsline {subsection}{\numberline {7.3.4}Prime Ministers of the United Kingdom}{211}{subsection.7.3.4}%
\contentsline {subsection}{\numberline {7.3.5}Iteration}{218}{subsection.7.3.5}%
\contentsline {section}{\numberline {7.4}PDFs}{219}{section.7.4}%
\contentsline {subsection}{\numberline {7.4.1}\emph {Jane Eyre}}{220}{subsection.7.4.1}%
\contentsline {subsection}{\numberline {7.4.2}Total Fertility Rate in the United States}{223}{subsection.7.4.2}%
\contentsline {subsection}{\numberline {7.4.3}Optical Character Recognition}{230}{subsection.7.4.3}%
\contentsline {section}{\numberline {7.5}Exercises}{233}{section.7.5}%
\contentsline {subsection}{Scales}{233}{section*.104}%
\contentsline {subsection}{Questions}{233}{section*.105}%
\contentsline {subsection}{Tutorial}{236}{section*.106}%
\contentsline {chapter}{\numberline {8}Hunt data}{237}{chapter.8}%
\contentsline {section}{\numberline {8.1}Introduction}{238}{section.8.1}%
\contentsline {section}{\numberline {8.2}Field experiments and randomized controlled trials}{241}{section.8.2}%
\contentsline {subsection}{\numberline {8.2.1}Randomization}{241}{subsection.8.2.1}%
\contentsline {subsection}{\numberline {8.2.2}Simulated example: cats or dogs}{242}{subsection.8.2.2}%
\contentsline {subsection}{\numberline {8.2.3}Treatment and control}{245}{subsection.8.2.3}%
\contentsline {subsection}{\numberline {8.2.4}Fisher's tea party}{248}{subsection.8.2.4}%
\contentsline {subsection}{\numberline {8.2.5}Ethical foundations}{249}{subsection.8.2.5}%
\contentsline {subsubsection}{\numberline {8.2.5.1}Tuskegee Syphilis Study}{249}{subsubsection.8.2.5.1}%
\contentsline {subsubsection}{\numberline {8.2.5.2}Extracorporeal membrane oxygenation (ECMO)}{250}{subsubsection.8.2.5.2}%
\contentsline {section}{\numberline {8.3}Surveys}{251}{section.8.3}%
\contentsline {subsection}{\numberline {8.3.1}Democracy Fund Voter Study Group}{253}{subsection.8.3.1}%
\contentsline {section}{\numberline {8.4}RCT examples}{256}{section.8.4}%
\contentsline {subsection}{\numberline {8.4.1}The Oregon Health Insurance Experiment}{256}{subsection.8.4.1}%
\contentsline {subsection}{\numberline {8.4.2}Civic Honesty Around The Globe}{257}{subsection.8.4.2}%
\contentsline {section}{\numberline {8.5}A/B testing}{260}{section.8.5}%
\contentsline {subsection}{\numberline {8.5.1}Upworthy}{263}{subsection.8.5.1}%
\contentsline {section}{\numberline {8.6}Exercises}{266}{section.8.6}%
\contentsline {subsection}{Scales}{266}{section*.111}%
\contentsline {subsection}{Questions}{266}{section*.112}%
\contentsline {subsection}{Tutorial}{267}{section*.113}%
\contentsline {subsection}{Paper}{267}{section*.114}%
\contentsline {part}{IV\hspace {1em}Preparation}{269}{part.4}%
\contentsline {chapter}{\numberline {9}Clean and prepare}{271}{chapter.9}%
\contentsline {section}{\numberline {9.1}Introduction}{272}{section.9.1}%
\contentsline {section}{\numberline {9.2}Workflow}{274}{section.9.2}%
\contentsline {subsection}{\numberline {9.2.1}Save the original, unedited data}{274}{subsection.9.2.1}%
\contentsline {subsection}{\numberline {9.2.2}Plan}{275}{subsection.9.2.2}%
\contentsline {subsection}{\numberline {9.2.3}Start small}{276}{subsection.9.2.3}%
\contentsline {subsection}{\numberline {9.2.4}Write tests and documentation}{278}{subsection.9.2.4}%
\contentsline {subsection}{\numberline {9.2.5}Iterate, generalize, and update}{283}{subsection.9.2.5}%
\contentsline {section}{\numberline {9.3}Checking and testing}{283}{section.9.3}%
\contentsline {subsection}{\numberline {9.3.1}Graphs}{283}{subsection.9.3.1}%
\contentsline {subsection}{\numberline {9.3.2}Counts}{284}{subsection.9.3.2}%
\contentsline {subsection}{\numberline {9.3.3}Tests}{285}{subsection.9.3.3}%
\contentsline {subsubsection}{\numberline {9.3.3.1}Aspects to test}{288}{subsubsection.9.3.3.1}%
\contentsline {subsubsection}{\numberline {9.3.3.2}Class}{290}{subsubsection.9.3.3.2}%
\contentsline {subsubsection}{\numberline {9.3.3.3}Dates}{292}{subsubsection.9.3.3.3}%
\contentsline {section}{\numberline {9.4}Simulated example: running times}{298}{section.9.4}%
\contentsline {section}{\numberline {9.5}Names}{301}{section.9.5}%
\contentsline {subsection}{\numberline {9.5.1}Machine-readable}{302}{subsection.9.5.1}%
\contentsline {subsection}{\numberline {9.5.2}Human-readable}{303}{subsection.9.5.2}%
\contentsline {section}{\numberline {9.6}1996 Tanzanian DHS}{305}{section.9.6}%
\contentsline {section}{\numberline {9.7}2019 Kenyan census}{311}{section.9.7}%
\contentsline {subsection}{\numberline {9.7.1}Gather and clean}{312}{subsection.9.7.1}%
\contentsline {subsubsection}{\numberline {9.7.1.1}Make rectangular}{312}{subsubsection.9.7.1.1}%
\contentsline {subsubsection}{\numberline {9.7.1.2}Validity}{315}{subsubsection.9.7.1.2}%
\contentsline {subsubsection}{\numberline {9.7.1.3}Internal consistency}{316}{subsubsection.9.7.1.3}%
\contentsline {subsection}{\numberline {9.7.2}Check and test}{316}{subsection.9.7.2}%
\contentsline {subsection}{\numberline {9.7.3}Tidy-up}{317}{subsection.9.7.3}%
\contentsline {section}{\numberline {9.8}Exercises}{320}{section.9.8}%
\contentsline {subsection}{Scales}{320}{section*.127}%
\contentsline {subsection}{Questions}{321}{section*.128}%
\contentsline {subsection}{Tutorial}{322}{section*.129}%
\contentsline {chapter}{\numberline {10}Store and share}{323}{chapter.10}%
\contentsline {section}{\numberline {10.1}Introduction}{324}{section.10.1}%
\contentsline {section}{\numberline {10.2}Plan}{325}{section.10.2}%
\contentsline {section}{\numberline {10.3}Share}{326}{section.10.3}%
\contentsline {subsection}{\numberline {10.3.1}GitHub}{326}{subsection.10.3.1}%
\contentsline {subsection}{\numberline {10.3.2}R packages for data}{327}{subsection.10.3.2}%
\contentsline {subsection}{\numberline {10.3.3}Depositing data}{329}{subsection.10.3.3}%
\contentsline {section}{\numberline {10.4}Data documentation}{330}{section.10.4}%
\contentsline {section}{\numberline {10.5}Personally identifying information}{331}{section.10.5}%
\contentsline {subsection}{\numberline {10.5.1}Hashing}{333}{subsection.10.5.1}%
\contentsline {subsection}{\numberline {10.5.2}Simulation}{335}{subsection.10.5.2}%
\contentsline {subsection}{\numberline {10.5.3}Differential privacy}{335}{subsection.10.5.3}%
\contentsline {section}{\numberline {10.6}Data efficiency}{338}{section.10.6}%
\contentsline {subsection}{\numberline {10.6.1}Iteration}{338}{subsection.10.6.1}%
\contentsline {subsection}{\numberline {10.6.2}Apache Arrow}{340}{subsection.10.6.2}%
\contentsline {section}{\numberline {10.7}Exercises}{342}{section.10.7}%
\contentsline {subsection}{Scales}{342}{section*.131}%
\contentsline {subsection}{Questions}{342}{section*.132}%
\contentsline {subsection}{Tutorial}{342}{section*.133}%
\contentsline {subsection}{Paper}{343}{section*.134}%
\contentsline {part}{V\hspace {1em}Modeling}{345}{part.5}%
\contentsline {chapter}{\numberline {11}Exploratory data analysis}{347}{chapter.11}%
\contentsline {section}{\numberline {11.1}Introduction}{348}{section.11.1}%
\contentsline {section}{\numberline {11.2}1975 United States population and income data}{349}{section.11.2}%
\contentsline {section}{\numberline {11.3}Missing data}{352}{section.11.3}%
\contentsline {section}{\numberline {11.4}TTC subway delays}{355}{section.11.4}%
\contentsline {subsection}{\numberline {11.4.1}Distribution and properties of individual variables}{357}{subsection.11.4.1}%
\contentsline {subsection}{\numberline {11.4.2}Relationships between variables}{367}{subsection.11.4.2}%
\contentsline {section}{\numberline {11.5}Airbnb listings in London, England}{369}{section.11.5}%
\contentsline {subsection}{\numberline {11.5.1}Distribution and properties of individual variables}{371}{subsection.11.5.1}%
\contentsline {subsection}{\numberline {11.5.2}Relationships between variables}{381}{subsection.11.5.2}%
\contentsline {section}{\numberline {11.6}Concluding remarks}{384}{section.11.6}%
\contentsline {section}{\numberline {11.7}Exercises}{385}{section.11.7}%
\contentsline {subsection}{Scales}{385}{section*.155}%
\contentsline {subsection}{Questions}{385}{section*.156}%
\contentsline {subsection}{Tutorial}{386}{section*.157}%
\contentsline {chapter}{\numberline {12}Linear models}{387}{chapter.12}%
\contentsline {section}{\numberline {12.1}Introduction}{388}{section.12.1}%
\contentsline {section}{\numberline {12.2}Simple linear regression}{389}{section.12.2}%
\contentsline {subsection}{\numberline {12.2.1}Simulated example: running times}{393}{subsection.12.2.1}%
\contentsline {section}{\numberline {12.3}Multiple linear regression}{401}{section.12.3}%
\contentsline {subsection}{\numberline {12.3.1}Simulated example: running times with rain and humidity}{401}{subsection.12.3.1}%
\contentsline {section}{\numberline {12.4}Building models}{408}{section.12.4}%
\contentsline {section}{\numberline {12.5}Concluding remarks}{416}{section.12.5}%
\contentsline {section}{\numberline {12.6}Exercises}{416}{section.12.6}%
\contentsline {subsection}{Scales}{416}{section*.171}%
\contentsline {subsection}{Questions}{417}{section*.172}%
\contentsline {subsection}{Tutorial}{417}{section*.173}%
\contentsline {subsection}{Paper}{418}{section*.174}%
\contentsline {chapter}{\numberline {13}Generalized linear models}{419}{chapter.13}%
\contentsline {section}{\numberline {13.1}Introduction}{420}{section.13.1}%
\contentsline {section}{\numberline {13.2}Logistic regression}{420}{section.13.2}%
\contentsline {subsection}{\numberline {13.2.1}Simulated example: day or night}{422}{subsection.13.2.1}%
\contentsline {subsection}{\numberline {13.2.2}Political support in the United States}{426}{subsection.13.2.2}%
\contentsline {section}{\numberline {13.3}Poisson regression}{433}{section.13.3}%
\contentsline {subsection}{\numberline {13.3.1}Simulated example: number of As by department}{434}{subsection.13.3.1}%
\contentsline {subsection}{\numberline {13.3.2}Letters used in \emph {Jane Eyre}}{437}{subsection.13.3.2}%
\contentsline {section}{\numberline {13.4}Negative binomial regression}{443}{section.13.4}%
\contentsline {subsection}{\numberline {13.4.1}Mortality in Alberta, Canada}{443}{subsection.13.4.1}%
\contentsline {section}{\numberline {13.5}Multilevel modeling}{450}{section.13.5}%
\contentsline {subsection}{\numberline {13.5.1}Simulated example: political support}{451}{subsection.13.5.1}%
\contentsline {subsection}{\numberline {13.5.2}Austen, Brontë, Dickens, and Shakespeare}{453}{subsection.13.5.2}%
\contentsline {section}{\numberline {13.6}Concluding remarks}{456}{section.13.6}%
\contentsline {section}{\numberline {13.7}Exercises}{457}{section.13.7}%
\contentsline {subsection}{Scales}{457}{section*.199}%
\contentsline {subsection}{Questions}{457}{section*.200}%
\contentsline {subsection}{Tutorial}{458}{section*.201}%
\contentsline {subsection}{Paper}{458}{section*.202}%
\contentsline {part}{VI\hspace {1em}Applications}{459}{part.6}%
\contentsline {chapter}{\numberline {14}Causality from observational data}{461}{chapter.14}%
\contentsline {section}{\numberline {14.1}Introduction}{462}{section.14.1}%
\contentsline {section}{\numberline {14.2}Directed Acyclic Graphs}{463}{section.14.2}%
\contentsline {subsection}{\numberline {14.2.1}Confounder}{463}{subsection.14.2.1}%
\contentsline {subsection}{\numberline {14.2.2}Mediator}{465}{subsection.14.2.2}%
\contentsline {subsection}{\numberline {14.2.3}Collider}{465}{subsection.14.2.3}%
\contentsline {section}{\numberline {14.3}Two common paradoxes}{467}{section.14.3}%
\contentsline {subsection}{\numberline {14.3.1}Simpson's paradox}{467}{subsection.14.3.1}%
\contentsline {subsection}{\numberline {14.3.2}Berkson's paradox}{470}{subsection.14.3.2}%
\contentsline {section}{\numberline {14.4}Difference-in-differences}{471}{section.14.4}%
\contentsline {subsection}{\numberline {14.4.1}Simulated example: tennis serve speed}{472}{subsection.14.4.1}%
\contentsline {subsection}{\numberline {14.4.2}Assumptions}{476}{subsection.14.4.2}%
\contentsline {subsection}{\numberline {14.4.3}French newspaper prices between 1960 and 1974}{477}{subsection.14.4.3}%
\contentsline {section}{\numberline {14.5}Propensity score matching}{481}{section.14.5}%
\contentsline {subsection}{\numberline {14.5.1}Simulated example: free shipping}{482}{subsection.14.5.1}%
\contentsline {section}{\numberline {14.6}Regression discontinuity design}{486}{section.14.6}%
\contentsline {subsection}{\numberline {14.6.1}Simulated example: income and grades}{487}{subsection.14.6.1}%
\contentsline {subsection}{\numberline {14.6.2}Assumptions}{490}{subsection.14.6.2}%
\contentsline {subsection}{\numberline {14.6.3}Alcohol and crime in California}{493}{subsection.14.6.3}%
\contentsline {section}{\numberline {14.7}Instrumental variables}{496}{section.14.7}%
\contentsline {subsection}{\numberline {14.7.1}Simulated example: health status, smoking, and tax rates}{498}{subsection.14.7.1}%
\contentsline {subsection}{\numberline {14.7.2}Assumptions}{501}{subsection.14.7.2}%
\contentsline {section}{\numberline {14.8}Exercises}{503}{section.14.8}%
\contentsline {subsection}{Scales}{503}{section*.229}%
\contentsline {subsection}{Questions}{503}{section*.230}%
\contentsline {subsection}{Tutorial}{504}{section*.231}%
\contentsline {chapter}{\numberline {15}Multilevel regression with post-stratification}{505}{chapter.15}%
\contentsline {section}{\numberline {15.1}Introduction}{506}{section.15.1}%
\contentsline {section}{\numberline {15.2}Simulated example: coffee or tea?}{509}{section.15.2}%
\contentsline {subsection}{\numberline {15.2.1}Construct a population and biased sample}{509}{subsection.15.2.1}%
\contentsline {subsection}{\numberline {15.2.2}Model the sample}{511}{subsection.15.2.2}%
\contentsline {subsection}{\numberline {15.2.3}Post-stratification dataset}{513}{subsection.15.2.3}%
\contentsline {section}{\numberline {15.3}Forecasting the 2020 United States election}{515}{section.15.3}%
\contentsline {subsection}{\numberline {15.3.1}Survey data}{515}{subsection.15.3.1}%
\contentsline {subsection}{\numberline {15.3.2}Post-stratification data}{516}{subsection.15.3.2}%
\contentsline {subsection}{\numberline {15.3.3}Model the sample}{517}{subsection.15.3.3}%
\contentsline {subsection}{\numberline {15.3.4}Post-stratify}{521}{subsection.15.3.4}%
\contentsline {section}{\numberline {15.4}Exercises}{524}{section.15.4}%
\contentsline {subsection}{Scales}{524}{section*.241}%
\contentsline {subsection}{Questions}{524}{section*.242}%
\contentsline {subsection}{Tutorial}{525}{section*.243}%
\contentsline {subsection}{Paper}{525}{section*.244}%
\contentsline {chapter}{\numberline {16}Text as data}{527}{chapter.16}%
\contentsline {section}{\numberline {16.1}Introduction}{528}{section.16.1}%
\contentsline {section}{\numberline {16.2}Text cleaning and preparation}{529}{section.16.2}%
\contentsline {subsection}{\numberline {16.2.1}Stop words}{530}{subsection.16.2.1}%
\contentsline {subsection}{\numberline {16.2.2}Case, numbers, and punctuation}{532}{subsection.16.2.2}%
\contentsline {subsection}{\numberline {16.2.3}Typos and uncommon words}{533}{subsection.16.2.3}%
\contentsline {subsection}{\numberline {16.2.4}Tuples}{534}{subsection.16.2.4}%
\contentsline {subsection}{\numberline {16.2.5}Stemming and lemmatizing}{536}{subsection.16.2.5}%
\contentsline {subsection}{\numberline {16.2.6}Duplication}{536}{subsection.16.2.6}%
\contentsline {section}{\numberline {16.3}Term Frequency-Inverse Document Frequency (TF-IDF)}{537}{section.16.3}%
\contentsline {subsection}{\numberline {16.3.1}Distinguishing horoscopes}{537}{subsection.16.3.1}%
\contentsline {section}{\numberline {16.4}Topic models}{540}{section.16.4}%
\contentsline {subsection}{\numberline {16.4.1}What is talked about in the Canadian parliament?}{542}{subsection.16.4.1}%
\contentsline {section}{\numberline {16.5}Exercises}{545}{section.16.5}%
\contentsline {subsection}{Scales}{545}{section*.247}%
\contentsline {subsection}{Questions}{545}{section*.248}%
\contentsline {subsection}{Tutorial}{546}{section*.249}%
\contentsline {chapter}{\numberline {17}Concluding remarks}{547}{chapter.17}%
\contentsline {section}{\numberline {17.1}Concluding remarks}{547}{section.17.1}%
\contentsline {section}{\numberline {17.2}Some outstanding issues}{548}{section.17.2}%
\contentsline {section}{\numberline {17.3}Next steps}{550}{section.17.3}%
\contentsline {section}{\numberline {17.4}Exercises}{552}{section.17.4}%
\contentsline {subsection}{Questions}{552}{section*.250}%
\contentsline {fm}{References}{553}{chapter*.252}%
\contentsline {chapter}{References}{553}{chapter*.252}%
\contentsline {chapter}{Index}{593}{chapter*.252}%
\contentsline {section}{}{593}{chapter*.252}%