Statistical Inference via Data Science: A ModernDive into R and the Tidyverse

Cover
Half Title
Title Page
Copyright Page
Dedication
Table of Contents
Foreword
Preface
About the authors
1: Getting Started with Data in R
	1.1 What are R and RStudio?
		1.1.1 Installing R and RStudio
		1.1.2 Using R via RStudio
	1.2 How do I code in R?
		1.2.1 Basic programming concepts and terminology
		1.2.2 Errors, warnings, and messages
		1.2.3 Tips on learning to code
	1.3 What are R packages?
		1.3.1 Package installation
		1.3.2 Package loading
		1.3.3 Package use
	1.4 Explore your first datasets
		1.4.1 nycflights13 package
		1.4.2 flights data frame
		1.4.3 Exploring data frames
		1.4.4 Identification and measurement variables
		1.4.5 Help files
	1.5 Conclusion
		1.5.1 Additional resources
		1.5.2 What’s to come?
I: Data Science with tidyverse
	2: Data Visualization
		2.1 The grammar of graphics
			2.1.1 Components of the grammar
			2.1.2 Gapminder data
			2.1.3 Other components
			2.1.4 ggplot2 package
		2.2 Five named graphs - the 5NG
		2.3 5NG#1: Scatterplots
			2.3.1 Scatterplots via geom_point
			2.3.2 Overplotting
			2.3.3 Summary
		2.4 5NG#2: Linegraphs
			2.4.1 Linegraphs via geom_line
			2.4.2 Summary
		2.5 5NG#3: Histograms
			2.5.1 Histograms via geom_histogram
			2.5.2 Adjusting the bins
			2.5.3 Summary
		2.6 Facets
		2.7 5NG#4: Boxplots
			2.7.1 Boxplots via geom_boxplot
			2.7.2 Summary
		2.8 5NG#5: Barplots
			2.8.1 Barplots via geom_bar or geom_col
			2.8.2 Must avoid pie charts!
			2.8.3 Two categorical variables
			2.8.4 Summary
		2.9 Conclusion
			2.9.1 Summary table
			2.9.2 Function argument specification
			2.9.3 Additional resources
			2.9.4 What’s to come
	3: Data Wrangling
		3.1 The pipe operator: %>%
		3.2 filter rows
		3.3 summarize variables
		3.4 group_by rows
			3.4.1 Grouping by more than one variable
		3.5 mutate existing variables
		3.6 arrange and sort rows
		3.7 join data frames
			3.7.1 Matching “key” variable names
			3.7.2 Different “key” variable names
			3.7.3 Multiple “key” variables
			3.7.4 Normal forms
		3.8 Other verbs
			3.8.1 select variables
			3.8.2 rename variables
			3.8.3 top_n values of a variable
		3.9 Conclusion
			3.9.1 Summary table
			3.9.2 Additional resources
			3.9.3 What’s to come?
	4: Data Importing and “Tidy” Data
		4.1 Importing data
			4.1.1 Using the console
			4.1.2 Using RStudio’s interface
		4.2 “Tidy” data
			4.2.1 Definition of “tidy” data
			4.2.2 Converting to “tidy” data
			4.2.3 nycflights13 package
		4.3 Case study: Democracy in Guatemala
		4.4 tidyverse package
		4.5 Conclusion
			4.5.1 Additional resources
			4.5.2 What’s to come?
II: Data Modeling with moderndive
	5: Basic Regression
		5.1 One numerical explanatory variable
			5.1.1 Exploratory data analysis
			5.1.2 Simple linear regression
			5.1.3 Observed/fitted values and residuals
		5.2 One categorical explanatory variable
			5.2.1 Exploratory data analysis
			5.2.2 Linear regression
			5.2.3 Observed/fitted values and residuals
		5.3 Related topics
			5.3.1 Correlation is not necessarily causation
			5.3.2 Best-fitting line
			5.3.3 get_regression_x() functions
		5.4 Conclusion
			5.4.1 Additional resources
			5.4.2 What’s to come?
	6: Multiple Regression
		6.1 One numerical and one categorical explanatory variable
			6.1.1 Exploratory data analysis
			6.1.2 Interaction model
			6.1.3 Parallel slopes model
			6.1.4 Observed/fitted values and residuals
		6.2 Two numerical explanatory variables
			6.2.1 Exploratory data analysis
			6.2.2 Regression plane
			6.2.3 Observed/fitted values and residuals
		6.3 Related topics
			6.3.1 Model selection
			6.3.2 Correlation coefficient
			6.3.3 Simpson’s Paradox
		6.4 Conclusion
			6.4.1 Additional resources
			6.4.2 What’s to come?
III: Statistical Inference with infer
	7: Sampling
		7.1 Sampling bowl activity
			7.1.1 What proportion of this bowl’s balls are red?
			7.1.2 Using the shovel once
			7.1.3 Using the shovel 33 times
			7.1.4 What did we just do?
		7.2 Virtual sampling
			7.2.1 Using the virtual shovel once
			7.2.2 Using the virtual shovel 33 times
			7.2.3 Using the virtual shovel 1000 times
			7.2.4 Using different shovels
		7.3 Sampling framework
			7.3.1 Terminology and notation
			7.3.2 Statistical definitions
			7.3.3 The moral of the story
		7.4 Case study: Polls
		7.5 Conclusion
			7.5.1 Sampling scenarios
			7.5.2 Central Limit Theorem
			7.5.3 Additional resources
			7.5.4 What’s to come?
	8: Bootstrapping and Confidence Intervals
		8.1 Pennies activity
			8.1.1 What is the average year on US pennies in 2019?
			8.1.2 Resampling once
			8.1.3 Resampling 35 times
			8.1.4 What did we just do?
		8.2 Computer simulation of resampling
			8.2.1 Virtually resampling once
			8.2.2 Virtually resampling 35 times
			8.2.3 Virtually resampling 1000 times
		8.3 Understanding confidence intervals
			8.3.1 Percentile method
			8.3.2 Standard error method
		8.4 Constructing confidence intervals
			8.4.1 Original workflow
			8.4.2 infer package workflow
			8.4.3 Percentile method with infer
			8.4.4 Standard error method with infer
		8.5 Interpreting confidence intervals
			8.5.1 Did the net capture the fish?
			8.5.2 Precise and shorthand interpretation
			8.5.3 Width of confidence intervals
		8.6 Case study: Is yawning contagious?
			8.6.1 Mythbusters study data
			8.6.2 Sampling scenario
			8.6.3 Constructing the confidence interval
			8.6.4 Interpreting the confidence interval
		8.7 Conclusion
			8.7.1 Comparing bootstrap and sampling distributions
			8.7.2 Theory-based confidence intervals
			8.7.3 Additional resources
			8.7.4 What’s to come?
	9: Hypothesis Testing
		9.1 Promotions activity
			9.1.1 Does gender affect promotions at a bank?
			9.1.2 Shuffling once
			9.1.3 Shuffling 16 times
			9.1.4 What did we just do?
		9.2 Understanding hypothesis tests
		9.3 Conducting hypothesis tests
			9.3.1 infer package workflow
			9.3.2 Comparison with confidence intervals
			9.3.3 “There is only one test”
		9.4 Interpreting hypothesis tests
			9.4.1 Two possible outcomes
			9.4.2 Types of errors
			9.4.3 How do we choose alpha?
		9.5 Case study: Are action or romance movies rated higher?
			9.5.1 IMDb ratings data
			9.5.2 Sampling scenario
			9.5.3 Conducting the hypothesis test
		9.6 Conclusion
			9.6.1 Theory-based hypothesis tests
			9.6.2 When inference is not needed
			9.6.3 Problems with p-values
			9.6.4 Additional resources
			9.6.5 What’s to come
	10: Inference for Regression
		10.1 Regression refresher
			10.1.1 Teaching evaluations analysis
			10.1.2 Sampling scenario
		10.2 Interpreting regression tables
			10.2.1 Standard error
			10.2.2 Test statistic
			10.2.3 p-value
			10.2.4 Confidence interval
			10.2.5 How does R compute the table?
		10.3 Conditions for inference for regression
			10.3.1 Residuals refresher
			10.3.2 Linearity of relationship
			10.3.3 Independence of residuals
			10.3.4 Normality of residuals
			10.3.5 Equality of variance
			10.3.6 What’s the conclusion?
		10.4 Simulation-based inference for regression
			10.4.1 Confidence interval for slope
			10.4.2 Hypothesis test for slope
		10.5 Conclusion
			10.5.1 Theory-based inference for regression
			10.5.2 Summary of statistical inference
			10.5.3 Additional resources
			10.5.4 What’s to come
IV: Conclusion
	11: Tell Your Story with Data
		11.1 Review
		11.2 Case study: Seattle house prices
			11.2.1 Exploratory data analysis: Part I
			11.2.2 Exploratory data analysis: Part II
			11.2.3 Regression modeling
			11.2.4 Making predictions
		11.3 Case study: Effective data storytelling
			11.3.1 Bechdel test for Hollywood gender representation
			11.3.2 US Births in 1999
			11.3.3 Scripts of R code
Appendix A: Statistical Background
	A.1 Basic statistical terms
		A.1.1 Mean
		A.1.2 Median
		A.1.3 Standard deviation
		A.1.4 Five-number summary
		A.1.5 Distribution
		A.1.6 Outliers
	A.2 Normal distribution
	A.3 log10 transformations
Appendix B: Versions of R Packages Used
Bibliography
Index