Foreword xiii

Preface xv

Acknowledgments xix

About the Author xxiii

1. Getting R 1

1.2 R Version 2

1.3 32-bit versus 64-bit 2

1.4 Installing 2

1.5 Revolution R Community Edition 10

1.6 Conclusion 11

2. The R Environment 13

2.1 Command Line Interface 14

2.2 RStudio 15

2.3 Revolution Analytics RPE 26

2.4 Conclusion 27

3. R Packages 29

3.1 Installing Packages 29

3.3 Building a Package 33

3.4 Conclusion 33

4. Basics of R 35

4.1 Basic Math 35

4.2 Variables 36

4.3 Data Types 38

4.4 Vectors 43

4.5 Calling Functions 49

4.6 Function Documentation 49

4.7 Missing Data 50

4.8 Conclusion 51

5. Advanced Data Structures 53

5.1 data.frames 53

5.2 Lists 61

5.3 Matrices 68

5.4 Arrays 71

5.5 Conclusion 72

6. Reading Data into R 73

6.1 Reading CSVs 73

6.2 Excel Data 74

6.3 Reading from Databases 75

6.4 Data from Other Statistical Tools 77

6.5 R Binary Files 77

6.6 Data Included with R 79

6.7 Extract Data from Web Sites 80

6.8 Conclusion 81

7. Statistical Graphics 83

7.1 Base Graphics 83

7.2 ggplot2 86

7.3 Conclusion 98

8. Writing R Functions 99

8.1 Hello, World! 99

8.2 Function Arguments 100

8.3 Return Values 103

8.4 do.call 104

8.5 Conclusion 104

9. Control Statements 105

9.1 if and else 105

9.2 switch 108

9.3 ifelse 109

9.4 Compound Tests 111

9.5 Conclusion 112

10. Loops, the Un-R Way to Iterate 113

10.1 for Loops 113

10.2 while Loops 115

10.3 Controlling Loops 115

10.4 Conclusion 116

11. Group Manipulation 117

11.1 Apply Family 117

11.2 aggregate 120

11.3 plyr 124

11.4 data.table 129

11.5 Conclusion 139

12. Data Reshaping 141

12.1 cbind and rbind 141

12.2 Joins 142

12.3 reshape2 149

12.4 Conclusion 153

13. Manipulating Strings 155

13.1 paste 155

13.2 sprintf 156

13.3 Extracting Text 157

13.4 Regular Expressions 161

13.5 Conclusion 169

14. Probability Distributions 171

14.1 Normal Distribution 171

14.2 Binomial Distribution 176

14.3 Poisson Distribution 182

14.4 Other Distributions 185

14.5 Conclusion 186

15. Basic Statistics 187

15.1 Summary Statistics 187

15.2 Correlation and Covariance 191

15.3 T-Tests 200

15.4 ANOVA 207

15.5 Conclusion 210

16. Linear Models 211

16.1 Simple Linear Regression 211

16.2 Multiple Regression 216

16.3 Conclusion 232

17. Generalized Linear Models 233

17.1 Logistic Regression 233

17.2 Poisson Regression 237

17.3 Other Generalized Linear Models 240

17.4 Survival Analysis 240

17.5 Conclusion 245

18. Model Diagnostics 247

18.1 Residuals 247

18.2 Comparing Models 253

18.3 Cross-Validation 257

18.4 Bootstrap 262

18.5 Stepwise Variable Selection 265

18.6 Conclusion 269

19. Regularization and Shrinkage 271

19.1 Elastic Net 271

19.2 Bayesian Shrinkage 290

19.3 Conclusion 295

20. Nonlinear Models 297

20.1 Nonlinear Least Squares 297

20.2 Splines 300

20.3 Generalized Additive Models 304

20.4 Decision Trees 310

20.5 Random Forests 312

20.6 Conclusion 313

21. Time Series and Autocorrelation 315

21.1 Autoregressive Moving Average 315

21.2 VAR 32221.3 GARCH 327

21.4 Conclusion 336

22. Clustering 337

22.1 K-means 337

22.2 PAM 345

22.3 Hierarchical Clustering 352

22.4 Conclusion 357

23. Reproducibility, Reports and Slide Shows with knitr 359

23.1 Installing a LATEX Program 359

23.2 LATEX Primer 360

23.3 Using knitr with LATEX 362

23.4 Markdown Tips 367

23.5 Using knitr and Markdown 368

23.6 pandoc 369

23.7 Conclusion 371

24. Building R Packages 373

24.1 Folder Structure 373

24.2 Package Files 373

24.3 Package Documentation 380

24.4 Checking, Building and Installing 383

24.5 Submitting to CRAN 384

24.6 C++ Code 384

24.7 Conclusion 390

• A Real-Life Resources 391
• A.1 Meetups 391
• A.2 Stackoverflow 392
• A.3 Twitter 393
• A.4 Conferences 393
• A.5 Web Sites 393
• A.6 Documents 394
• A.7 Books 394
• A.8 Conclusion 394
• B Glossary 395

List of Figures 409

List of Tables 417

General Index 419

Index of Functions 427

Index of Packages 431

Index of People 433

Data Index 435

Jared Lander is the Chief Data Scientist of Lander Analytics a New York data science firm, Adjunct Professor at Columbia University, Organizer of the New York Open Statistical Programming meetup and the New York and Washington DC R Conferences and author of R for Everyone.