Data Science for All, Global Edition

About our authors Brennan Davis is the Richard and Julie Hood Professor and director of graduate analytics programs at the Orfalea College of Business at California Polytechnic State University (Cal Poly, San Luis Obispo). He received a BS in mathematics from the University of California, Los Angeles, an MBA from the Wharton School of Business at the University of Pennsylvania, and a PhD from the University of California, Irvine. Brennan currently teaches undergraduate and graduate analytics courses. In 2019, Brennan received the Emeritus Faculty Award for significant and meritorious achievement in contributing to student welfare.Hunter Glanz is a Professor of Statistics and Data Science at California Polytechnic State University (Cal Poly, San Luis Obispo). He received a BS in mathematics and a BS in statistics from Cal Poly, followed by an MA and PhD in statistics from Boston University. He maintains a passion for data science, machine learning, and statistical computing and enjoys teaching courses in those areas. Hunter serves on numerous committees and organizations dedicated to delivering cutting-edge statistical and data science content to students and professionals alike, including being a founding board member of the California Alliance for Data Science Education. In 2019, Hunter received the Terrance Harris Excellence in Mentorship Award, and in 2020 he received the Outstanding Faculty Award in the Master’s in Business Analytics program at Cal Poly.

• 1: What Is Data Science? 1.1: Introduction to Data ScienceCase Study: Netflix Uses Data Science for a Better Customer Experience SectionCase Study: NASA Uses Cloud Services to Stream Real-Time Mars Footage Section1.2: Data in Tables1.3: Data Preparation1.4: Data Analysis and Storytelling1.5: Data Science in Society and IndustryCase Study: Amazon Uses Data for Customers, Ads, and Fraud PreventionPutting It TogetherEthics in Practice: Some Risks in Data ScienceChapter Review Questions2: Data Wrangling: Preprocessing 2.1: What Is Data Wrangling?2.2: Cleaning Missing DataCase Study: Data Wrangling in Criminal Justice Research2.3: Cleaning Anomalous ValuesCase Study: Conservative Party Defeats Labour Party in the UK and the Role of Data Wrangling2.4: Transforming Quantitative VariablesCase Study: GlobalGiving Teaches Nonprots About Transforming Variables2.5: Transforming Categorical Variables2.6: Reshaping a Dataset2.7: Combining DatasetsPutting It TogetherEthics in Practice: OtheringChapter Review Questions3: Making Sense of Data Through Visualization Case Study: Visualization of Natural Hazards3.1: The Grammar of Graphics3.2: Visualizations with One Quantitative Variable3.3: Visualizations with One Categorical Variable3.4: Visualizations with Two Variables3.5: Visualizations with Three or More Variables3.6: The Dangers of Visual Misrepresentation3.7: Data Visualization GuidelinesCase Study: European Space Agency Offers Interactive Star MapperCase Study: Real-Time Visualization and Disease OutbreaksPutting It TogetherEthics in Practice: The Perils of Using ColorChapter Review Questions4: Exploratory Data Analysis Case Study: Shopify Helps Small Businesses with Descriptive Analytics Section4.1: Central Tendency4.2: VariabilityCase Study: On- and Off-Field Exploratory Data Analysis in Sports Section4.3: Shape4.4: Resistant Central Tendency and Variability4.5: Data AssociationsCase Study: Exploratory Data Analysis of Electronic Medical Records Section4.6: Identifying OutliersPutting It TogetherEthics in Practice: Simpson’s ParadoxChapter Review Questions5: Data Management 5.1: Asking Questions of Data5.2: Selecting VariablesCase Study: Starbucks Queries Its Customer Data5.3: Filtering and Ordering ObservationsCase Study: Zara Filters to Move Its Product Faster5.4: Summarizing and Structuring Data5.5: Merging TablesCase Study: Merging Data to Combat the Spread of DiseasePutting It TogetherEthics in Practice: Data Privacy RegulationChapter Review Questions6: Understanding Uncertainty, Probability, and Variability 6.1: Variability and Uncertainty6.2: ProbabilityCase Study: The Economist’s French Presidential Election Model6.3: Sampling MethodsCase Study: Data Analytics in Cricket and Table Tennis6.4: Simulation6.5: Working with Probabilities and Common FallaciesCase Study: The Base Rate Fallacy of COVID-19 Misinformation in IcelandPutting It TogetherEthics in Practice: Power in SamplingChapter Review Questions7: Drawing Conclusions from Data 7.1: Introduction to Statistical Inference7.2: Data Collection and Study DesignCase Study: Firearm Regulations and Causation Versus Correlation Section7.3: The Language of Statistical Inference7.4: Exploratory Data Analysis to Begin Inference7.5: Drawing Conclusions in an Observational Study7.6: A/B Testing as a Case of ExperimentsCase Study: A/B Testing Rating Systems at NetflixPutting It TogetherEthics in Practice: P-Hacking and the Reproducibility CrisisChapter Review Questions8: Machine Learning 8.1: Artificial Intelligence8.2: Three Steps in the Machine Learning ProcessCase Study: How Tesla Uses Machine Learning8.3: Characteristics of Machine Learning Methods8.4: Machine Learning Method Evaluation Section8.5: Deep LearningCase Study: ChatGPTCase Study: Improving Safety in the Construction Industry Through Deep Learning8.6: Use High-Quality Data in Machine LearningPutting It TogetherEthics in Practice: Social Justice in Data ScienceChapter Review Questions9: Supervised Learning 9.1: Linear Regression with a No Explanatory Variables9.2: Linear Regression with a Categorical Explanatory Variable9.3: Linear Regression with a Quantitative Explanatory Variable9.4: Multiple Linear RegressionCase Study: Anesthesia and Regression9.5: Nonparametric Regression ModelsCase Study: Improving Student Success and Satisfaction in Higher Education9.6: Classification ModelsPutting It TogetherEthics in Practice: ExtrapolationChapter Review Questions10: Unsupervised Learning 10.1: What Is Unsupervised Learning?Case Study: Anomaly Detection at Accenture10.2: Getting to Know Cluster Analysis10.3: Introduction to K-Means ClusteringCase Study: Spotify Uses Unsupervised Machine Learning for Personalization10.4: Introduction to Hierarchical Clustering10.5: Assessing the Quality of ClustersCase Study: Clustering and Targeting AdvertisingPutting It TogetherEthics in Practice: Subjectivity in Unsupervised LearningChapter Review QuestionsAppendices A: Guide to Data Science SoftwareB: Answers