With its flexible capabilities and open-source platform, R has become a major tool for analyzing detailed, high-quality baseball data. Analyzing Baseball Data with R provides an introduction to R for sabermetricians, baseball enthusiasts, and students interested in exploring the rich sources of baseball data. It equips readers with the necessary skills and software tools to perform all of the analysis steps, from gathering the datasets and entering them in a convenient format to visualizing the data via graphs to performing a statistical analysis.
The authors first present an overview of publicly available baseball datasets and a gentle introduction to the type of data structures and exploratory and data management capabilities of R. They also cover the traditional graphics functions in the base package and introduce more sophisticated graphical displays available through the lattice and ggplot2 packages. Much of the book illustrates the use of R through popular sabermetrics topics, including the Pythagorean formula, runs expectancy, career trajectories, simulation of games and seasons, patterns of streaky behavior of players, and fielding measures. Each chapter contains exercises that encourage readers to perform their own analyses using R. All of the datasets and R code used in the text are available online.
This book helps readers answer questions about baseball teams, players, and strategy using large, publically available datasets. It offers detailed instructions on downloading the datasets and putting them into formats that simplify data exploration and analysis. Through the book’s various examples, readers will learn about modern sabermetrics and be able to conduct their own baseball analyses.
Table of Contents
The Baseball Datasets
The Lahman Database: Season-by-Season Data
Retrosheet Game-by-Game Data
Retrosheet Play-by-Play Data
Introduction to R
Installing R and RStudio
Objects and Containers in R
Collection of R Commands
Reading and Writing Data in R
Splitting, Applying, and Combining Data
Numeric Variable: Stripchart and Histogram
Two Numeric Variables
A Numeric Variable and a Factor Variable
Comparing Ruth, Aaron, Bonds, and A-Rod
The 1998 Home Run Race
The Relation between Runs and Wins
The Teams Table in Lahman's Database
The Pythagorean Formula for Winning Percentage
The Exponent in the Pythagorean Formula
Good and Bad Predictions by the Pythagorean Formula
How Many Runs for a Win?
Value of Plays Using Run Expectancy
The Runs Expectancy Matrix
Runs Scored in the Remainder of the Inning
Creating the Matrix
Measuring Success of a Batting Play
Opportunity and Success for All Hitters
Position in the Batting Lineup
Run Values of Different Base Hits
Value of Base Stealing
The lattice Package
The ggplot2 Package
Balls and Strikes Effects
Hitter's Counts and Pitcher's Counts
Behaviors by Count
Mickey Mantle's Batting Trajectory
General Patterns of Peak Ages
Trajectories and Fielding Position
Simulating a Half Inning
Simulating a Baseball Season
Exploring Streaky Performances
The Great Streak
Streaks in Individual At-Bats
Local Patterns of Weighted On-Base Average
Learning about Park Effects by Database Management Tools
Installing MySQL and Creating a Database
Connecting R to MySQL
Filling a MySQL Game Log Database from R
Querying Data from R
Baseball Data as MySQL Dumps
Calculating Basic Park Factors
Exploring Fielding Metrics with Contributed R Packages
A Motivating Example: Comparing Fielding Metrics
Comparing Two Shortstops
Appendix A: Retrosheet Files Reference
Appendix B: Accessing and Using MLBAM Gameday and PITCHf/x Data
Further Reading and Exercises appear at the end of each chapter.
Max Marchi is a baseball analyst with the Cleveland Indians. He was previously a statistician at the Emilia-Romagna Regional Health Agency. He has been a regular contributor to The Hardball Times and Baseball Prospectus websites and has consulted for MLB clubs.
Jim Albert is a professor of statistics at Bowling Green State University. He has authored or coauthored several books and is the editor of the Journal of Quantitative Analysis of Sports. His interests include Bayesian modeling, statistics education, and the application of statistical thinking in sports.
"There are some great resources out there for learning R and for learning how to analyze baseball data with it. In fact, a few pretty smart people wrote a fantastic book on the subject, coincidentally titled Analyzing Baseball Data with R. I can’t say enough about this book as a reference, both for baseball analysis and for R. Go and buy it."
—Bill Petti, The Hardball Times, September 2015
"The authors present a potpourri of well-conceived case-studies that give insight into both the game’s complexity and R’s simplicity. Virtually no previous knowledge of statistical theory and software is required to master the data analyses and to follow the explications in this book … The authors’ style of writing is pleasurable and bespeaks their passion for the game. Narratives and R commands are so smoothly intermingled that the source code hardly disturbs the flow of reading, and a wealth of graphs break up the grey. … A great asset of the book is that it encourages the reader to learn the ropes of sabermetrics by actually running the example analyses on one’s own computer."
—Journal of the Royal Statistical Society, Series A, 2015
"If you are interested in statistics, especially baseball statistics, you will find this book fascinating and very useful. It provides many details. websites, and useful descriptions for using the R programming environment. This is not only a book on statistics; there are many references to famous player statistics, making this a very enjoyable book to read. And even if you don’t like baseball but still find statistics very exciting, then this book provides a great introduction to R that can be used for any other type of statistical data set."
—IEEE Insulation Magazine, November/December 2014
"I have spent most of the past decade working in baseball as a statistical analyst for the New York Mets. … This type of employment can be highly valued, especially among quantitatively inclined college students who are coincidentally passionate baseball fans. It is from these students from whom I am most frequently asked, ‘what book would you recommend for someone who wants to get started in sabermetrics?’ Invariably, my response has been [Jim Albert and Jay Bennett’s] Curve Ball. I have a new response. …
I always felt that Curve Ball was the best place for a budding sabermetrician to start … However, it later dawned on me that while Curve Ball provided a sound framework for thinking probabilistically about baseball, I devoted a huge proportion of my time at work to computer programming. …
In their new book, Albert and Max Marchi, a native Italian who now works for the Cleveland Indians, have closed the loop by offering the aspiring sabermetrician a blueprint. … The reader who digests this book alongside her keyboard will emerge as a practicing sabermetrician—having knowledge of the key ideas in sabermetric theory, a historical understanding of from whence those ideas came, and the practical ability to compute with baseball data. It is a sabermetric workshop in paperback."
—Ben S. Baumer, International Statistical Review (2014), 82