Stats: Data and Models, Global Edition

About our authors Richard D. De Veaux is an internationally known educator and consultant. He has taught at the Wharton School and the Princeton University School of Engineering, where he won a Lifetime Award for Dedication and Excellence in Teaching. He is the C. Carlisle and M. Tippit Professor and Chair of the Statistics Department at Williams College, where he has taught since 1994. Dick has won both the Wilcoxon and Shewell awards from the American Society for Quality. He is a fellow of the American Statistical Association (ASA) and an elected member of the International Statistical Institute (ISI). In 2008, he was named Statistician of the Year by the Boston Chapter of the ASA and was the 2018–2021 Vice-President of the ASA. Dick is also well known in industry, where for more than 30 years he has consulted for such Fortune 500 companies as American Express, Hewlett-Packard, Alcoa, DuPont, Pillsbury, General Electric, and Chemical Bank. Because he consulted with Mickey Hart on his book Planet Drum, he has also sometimes been called the “Official Statistician for the Grateful Dead.” His real-world experiences and anecdotes illustrate many of this book’s chapters.Dick holds degrees from Princeton University in Civil Engineering (B.S.E.) and Mathematics (A.B.) and from Stanford University in Dance Education (M.A.) and Statistics (Ph.D.), where he studied dance with Inga Weiss and Statistics with Persi Diaconis. His research focuses on the analysis of large data sets and data mining in science and industry. In his spare time, he is an avid cyclist and swimmer. He also is the founder of the “Diminished Faculty,” an a cappella Doo-Wop quartet at Williams College and sings bass in the college concert choir and with the Choeur Vittoria of Paris. Dick is the father of 4 children.Paul F. Velleman has an international reputation for innovative Statistics education. He is the author and designer of the multimedia Statistics program ActivStats, for which he was awarded the EDUCOM Medal for innovative uses of computers in teaching statistics, and the ICTCM Award for Innovation in Using Technology in College Mathematics. He also developed the award-winning statistics program, Data Desk, the Internet site Data and Story Library (DASL) (DASL.datadescription.com), which provides data sets for teaching Statistics (and is one source for the datasets used in this text.), and the tools referenced in the text for simulation and bootstrapping. Paul’s understanding of using and teaching with technology informs much of this book’s approach.Paul taught Statistics at Cornell University, where he was awarded the MacIntyre Award for Exemplary Teaching. He is Emeritus Professor of Statistical Science from Cornell and lives in Maine with his wife, Sue Michlovitz. He holds an A.B. from Dartmouth College in Mathematics and Social Science, and M.S. and Ph.D. degrees in Statistics from Princeton University, where he studied with John Tukey. His research often deals with statistical graphics and data analysis methods. Paul co-authored (with David Hoaglin) ABCs of Exploratory Data Analysis. Paul is a Fellow of the American Statistical Association and of the American Association for the Advancement of Science. Paul is the father of 2 boys. In his spare time he sings with the a capella group VoXX and studies tai chi.David E. Bock taught mathematics at Ithaca High School for 35 years. He has taught Statistics at Ithaca High School, Tompkins-Cortland Community College, Ithaca College, and Cornell University. Dave has won numerous teaching awards, including the MAA’s Edyth May Sliffe Award for Distinguished High School Mathematics Teaching (twice), Cornell University’s Outstanding Educator Award (three times), and has been a finalist for New York State Teacher of the Year.Dave holds degrees from the University at Albany in Mathematics (B.A.) and Statistics/Education (M.S.). Dave has been a reader and table leader for the AP Statistics exam, serves as a Statistics consultant to the College Board, and leads workshops and institutes for AP Statistics teachers. He has served as K–12 Education and Outreach Coordinator and a senior lecturer for the Mathematics Department at Cornell University. His understanding of how students learn informs much of this book’s approach.Dave and his wife relax by biking or hiking, spending much of their free time in Canada, the Rockies, or the Blue Ridge Mountains. They have a son, a daughter, and 4 grandchildren.

• I: EXPLORING AND UNDERSTANDING DATA 1. Stats Starts Here 1.1 What Is Statistics?1.2 Data1.3 Variables1.4 Models 2. Displaying and Describing Data 2.1 Summarizing and Displaying a Categorical Variable2.2 Displaying a Quantitative Variable2.3 Shape2.4 Center2.5 Spread 3. Relationships Between Categorical Variables–Contingency Tables 3.1 Contingency Tables3.2 Conditional Distributions3.3 Displaying Contingency Tables3.4 Three Categorical Variables 4. Understanding and Comparing Distributions 4.1 Displays for Comparing Groups4.2 Outliers4.3 Re-Expressing Data: A First Look 5. The Standard Deviation as a Ruler and the Normal Model 5.1 Using the Standard Deviation to Standardize Values5.2 Shifting and Scaling5.3 Normal Models5.4 Working with Normal Percentiles5.5 Normal Probability PlotsReview of Part I: Exploring and Understanding Data II. EXPLORING RELATIONSHIPS BETWEEN VARIABLES 6. Scatterplots, Association, and Correlation 6.1 Scatterplots6.2 Correlation6.3 Warning: Correlation ≠ Causation6.4 Straightening Scatterplots 7. Linear Regression 7.1 Least Squares: The Line of “Best Fit”7.2 The Linear Model7.3 Finding the Least Squares Line7.4 Regression to the Mean7.5 Examining the Residuals7.6 R2: The Variation Accounted for by the Model7.7 Regression Assumptions and Conditions 8. Regression Wisdom 8.1 Examining Residuals8.2 Extrapolation: Reaching Beyond the Data8.3 Outliers, Leverage, and Influence8.4 Lurking Variables and Causation8.5 Working with Summary Values8.6 Straightening Scatterplots: The Three Goals8.7 Finding a Good Re-Expression 9. Multiple Regression 9.1 What Is Multiple Regression?9.2 Interpreting Multiple Regression Coefficients9.3 The Multiple Regression Model: Assumptions and Conditions9.4 Partial Regression Plots9.5 Indicator VariablesReview of Part II: Exploring Relationships Between Variables III. GATHERING DATA 10. Sample Surveys 10.1 The Three Big Ideas of Sampling10.2 Populations and Parameters10.3 Simple Random Samples10.4 Other Sampling Designs10.5 From the Population to the Sample: You Can't Always Get What You Want10.6 The Valid Survey10.7 Common Sampling Mistakes, or How to Sample Badly 11. Experiments and Observational Studies 11.1 Observational Studies11.2 Randomized, Comparative Experiments11.3 The Four Principles of Experimental Design11.4 Control Groups11.5 Blocking11.6 ConfoundingReview of Part III: Gathering Data IV. RANDOMNESS AND PROBABILITY 12. From Randomness to Probability 12.1 Random Phenomena12.2 Modeling Probability12.3 Formal Probability 13. Probability Rules! 13.1 The General Addition Rule13.2 Conditional Probability and the General Multiplication Rule13.3 Independence13.4 Picturing Probability: Tables, Venn Diagrams, and Trees13.5 Reversing the Conditioning and Bayes' Rule 14. Random Variables 14.1 Center: The Expected Value14.2 Spread: The Standard Deviation14.3 Shifting and Combining Random Variables14.4 Continuous Random Variables 15. Probability Models 15.1 Bernoulli Trials15.2 The Geometric Model15.3 The Binomial Model15.4 Approximating the Binomial with a Normal Model15.5 The Continuity Correction15.6 The Poisson Model15.7 Other Continuous Random Variables: The Uniform and the ExponentialReview of Part IV: Randomness and Probability V. INFERENCE FOR ONE PARAMETER 16. Sampling Distribution Models and Confidence Intervals for Proportions 16.1 The Sampling Distribution Model for a Proportion16.2 When Does the Normal Model Work? Assumptions and Conditions16.3 A Confidence Interval for a Proportion16.4 Interpreting Confidence Intervals: What Does 95% Confidence Really Mean?16.5 Margin of Error: Certainty vs. Precision16.6 Choosing the Sample Size 17. Confidence Intervals for Means 17.1 The Central Limit Theorem17.2 A Confidence Interval for the Mean17.3 Interpreting Confidence Intervals17.4 Picking Our Interval up by Our Bootstraps17.5 Thoughts About Confidence Intervals 18. Testing Hypotheses 18.1 Hypotheses18.2 P-Values18.3 The Reasoning of Hypothesis Testing18.4 A Hypothesis Test for the Mean18.5 Intervals and Tests18.6 P-Values and Decisions: What to Tell About a Hypothesis Test 19. More About Tests and Intervals 19.1 Interpreting P-Values19.2 Alpha Levels and Critical Values19.3 Practical vs. Statistical Significance19.4 ErrorsReview of Part V: Inference for One Parameter VI. INFERENCE FOR RELATIONSHIPS 20. Comparing Groups 20.1 A Confidence Interval for the Difference Between Two Proportions20.2 Assumptions and Conditions for Comparing Proportions20.3 The Two-Sample z-Test: Testing for the Difference Between Proportions20.4 A Confidence Interval for the Difference Between Two Means20.5 The Two-Sample t-Test: Testing for the Difference Between Two Means20.6 Randomization Tests and Confidence Intervals for Two Means20.7 Pooling20.8 The Standard Deviation of a Difference 21. Paired Samples and Blocks 21.1 Paired Data21.2 The Paired t-Test21.3 Confidence Intervals for Matched Pairs21.4 Blocking 22. Comparing Counts 22.1 Goodness-of-Fit Tests22.2 Chi-Square Test of Homogeneity22.3 Examining the Residuals22.4 Chi-Square Test of Independence 23. Inferences for Regression 23.1 The Regression Model23.2 Assumptions and Conditions23.3 Regression Inference and Intuition23.4 The Regression Table23.5 Multiple Regression Inference23.6 Confidence and Prediction Intervals23.7 Logistic Regression23.8 More About RegressionReview of Part VI: Inference for Relationships VII. INFERENCE WHEN VARIABLES ARE RELATED 24. Multiple Regression Wisdom 24.1 Multiple Regression Inference24.2 Comparing Multiple Regression Model24.3 Indicators24.4 Diagnosing Regression Models: Looking at the Cases24.5 Building Multiple Regression Models 25. Analysis of Variance 25.1 Testing Whether the Means of Several Groups Are Equal25.2 The ANOVA Table25.3 Assumptions and Conditions25.4 Comparing Means25.5 ANOVA on Observational Data 26. Multifactor Analysis of Variance 26.1 A Two Factor ANOVA Model26.2 Assumptions and Conditions26.3 Interactions 27. Statistics and Data Science 27.1 Introduction to Data Mining27.2 The Data Science Workflow27.3 Statistical and Machine Learning Algorithms: A Sample27.4 Models Built from Combining Other Models27.5 Comparing Models27.6 SummaryReview of Part VII: Inference When Variables Are Related Parts I - V Cumulative Review ExercisesAppendices AnswersCreditsIndexesTables and Selected Formulas