| |
| |
Introduction | |
| |
| |
| |
Simple Models from Tabletop Baseball Games | |
| |
| |
All-Star Baseball (ASB) | |
| |
| |
Model Assumptions of All-Star Baseball | |
| |
| |
The APBA Model: Introducing the Pitcher | |
| |
| |
Strat-O-Matic Baseball: The Independent Model | |
| |
| |
Sports Illustrated Baseball: The Interactive Model | |
| |
| |
Which Model Is Best? | |
| |
| |
| |
Exploring Baseball Data | |
| |
| |
Exploring Hitting Data | |
| |
| |
A Batch of On-Base Percentages | |
| |
| |
Simple Graphs | |
| |
| |
Typical Values--the Mean and the Median | |
| |
| |
Measures of Spread--Quartiles and the Standard Deviation | |
| |
| |
Interesting Values | |
| |
| |
Comparing Groups | |
| |
| |
A Five-Number Summary | |
| |
| |
A Boxplot | |
| |
| |
Boxplots to Compare Groups | |
| |
| |
OBPs of Offensive and Defensive Players | |
| |
| |
Relationships Between Batting Measures | |
| |
| |
Relating OBP and SLG | |
| |
| |
Relating OBP and Isolated Power | |
| |
| |
What about Pitching Data? | |
| |
| |
Strikeouts and Walks | |
| |
| |
Looking at Strikeout Totals | |
| |
| |
Defining a Strikeout Rate | |
| |
| |
Comparing Strikeout Rates of Starters and Relievers | |
| |
| |
Association Between Strikeouts and Walks? | |
| |
| |
Exploring Walk Rates | |
| |
| |
Comparing Walk Rates of Starters and Relievers | |
| |
| |
| |
Introducing Probability | |
| |
| |
Beyond Data Analysis | |
| |
| |
Looking for Real Effects | |
| |
| |
Predicting OBPs | |
| |
| |
Probability Models | |
| |
| |
A Coin-Toss Model | |
| |
| |
Observed and True OBPs | |
| |
| |
Learning about Batting Ability | |
| |
| |
Estimating Batting Ability Using a Confidence Interval | |
| |
| |
Comparing Hitters | |
| |
| |
| |
Situational Effects | |
| |
| |
Surveying the Situation | |
| |
| |
Looking for Real Effects | |
| |
| |
Observed and True Batting Averages | |
| |
| |
Batting Averages of the 1998 Regulars | |
| |
| |
Two Models for Batting Averages | |
| |
| |
A .276 Spinner Model | |
| |
| |
Do All Players Have the Same Ability? | |
| |
| |
A Model Using a Set of Random Spinners | |
| |
| |
Situational Effects | |
| |
| |
Home vs. Away | |
| |
| |
Turf vs. Grass | |
| |
| |
The Count | |
| |
| |
Opposite Arm vs. Same Arm | |
| |
| |
Models for Situational Effects | |
| |
| |
Scenario 1 (No Situational Effect) | |
| |
| |
Scenario 2 (Situational Bias) | |
| |
| |
Scenario 3 (Situational Effect Depends on Ability) | |
| |
| |
Finding Good Models | |
| |
| |
What Do Observed Situational Effects Look Like When There Is No Effect? | |
| |
| |
The Last Five Years' Data | |
| |
| |
The "No Effect" Situations | |
| |
| |
The "Bias" Situations | |
| |
| |
The "Ability" Situations | |
| |
| |
How Large Are the True Ability Effects? | |
| |
| |
Game Situation Effects | |
| |
| |
A Lot of Noise | |
| |
| |
| |
Streakiness (Or, the Hot Hand) | |
| |
| |
Thinking about Streakiness | |
| |
| |
Interpreting Baseball Data | |
| |
| |
Moving Averages--Looking at Short Intervals | |
| |
| |
Runs of Good and Bad Games | |
| |
| |
Numbers of Good and Poor Hitting Days | |
| |
| |
What Is Zeile's True Hitting Ability? | |
| |
| |
Mr. Consistent | |
| |
| |
How Does Mr. Consistent Perform During a Season? | |
| |
| |
Mr. Streaky | |
| |
| |
How Does Mr. Streaky Perform During a Season? | |
| |
| |
Mr. Consistent or Mr. Streaky? | |
| |
| |
Team Play | |
| |
| |
A Consistent Team | |
| |
| |
A Streaky Team | |
| |
| |
Thinking about Streakiness--Again | |
| |
| |
| |
Measuring Offensive Performance | |
| |
| |
The Great Quest | |
| |
| |
Runs Scored per Game | |
| |
| |
Batting Average and Runs Scored per Game | |
| |
| |
Slugging Percentage and On-Base Percentage | |
| |
| |
Intuitive Techniques | |
| |
| |
On-Base Plus Slugging (OPS) | |
| |
| |
Total Average (TA) | |
| |
| |
Batter's Run Average (BRA) and Scoring Index (DX) | |
| |
| |
Runs Created (RC) | |
| |
| |
More Analytic Models | |
| |
| |
| |
Average Runs Per Play | |
| |
| |
Finding Weights for Plays | |
| |
| |
Least Squares Linear Regression (LSLR) | |
| |
| |
Adding Caught Stealing to the LSLR Model | |
| |
| |
Adding Sacrifice Flies to the LSLR Model | |
| |
| |
The Lindsey-Palmer Models | |
| |
| |
George Lindsey's Analysis | |
| |
| |
Palmer Enters the Picture | |
| |
| |
Comparing the LSLR and Lindsey-Palmer Models | |
| |
| |
| |
The Curvature of Baseball | |
| |
| |
The DLSI Simulation Model | |
| |
| |
The Probability of Scoring Two Runs | |
| |
| |
The Probability of Scoring No Runs | |
| |
| |
A DLSI Example | |
| |
| |
Lessons from the Simulation | |
| |
| |
DLSI and Runs per Play | |
| |
| |
Where Do We Stand? | |
| |
| |
Additive Models | |
| |
| |
Product Models | |
| |
| |
Player Evaluations in the Best Models | |
| |
| |
Player Evaluations on an Average Team | |
| |
| |
Sorting Out Strengths and Weaknesses | |
| |
| |
| |
Measuring Clutch Play | |
| |
| |
Clutch Hits | |
| |
| |
Leading Off an Inning vs. Not Leading Off | |
| |
| |
Runners in Scoring Position vs. Bases Empty | |
| |
| |
Runner in Scoring Position vs. Runner on First Base Only | |
| |
| |
Two Outs vs. None/One Out | |
| |
| |
Late Inning Pressure vs. No Late Inning Pressure | |
| |
| |
A Player in a Short Series | |
| |
| |
Situation Evaluation of Run Production | |
| |
| |
A New Criterion for Performance | |
| |
| |
The Calculation of Win Probabilities | |
| |
| |
Player Game Percentage (PGP) | |
| |
| |
World Series Most Valuable Players | |
| |
| |
Looking to the Future | |
| |
| |
| |
Prediction | |
| |
| |
Predicting Game Results | |
| |
| |
Guessing | |
| |
| |
Picking the Home Team | |
| |
| |
A "Team Strengths" Prediction Model | |
| |
| |
Predicting 1999 Game Results | |
| |
| |
How Good Were Our Predictions? | |
| |
| |
Predicting the Number of McGwire and Sosa Home Runs | |
| |
| |
A Simple Prediction Method | |
| |
| |
What's Wrong with This Prediction? | |
| |
| |
A Spinner Model for Home-Run Hitting | |
| |
| |
How Many At-Bats? | |
| |
| |
What If We Knew Sosa's True Home-Run Rate? | |
| |
| |
Binomial Probabilities | |
| |
| |
What If We Don't Know Sosa's True Home-Run Rate? | |
| |
| |
Revising Our Beliefs about Sosa's Home-Run Probability | |
| |
| |
One Prediction | |
| |
| |
Many Predictions | |
| |
| |
Predicting Career Statistics | |
| |
| |
Sosa's Home-Run Probabilities | |
| |
| |
How Long and How Many At-Bats? | |
| |
| |
Making the Predictions | |
| |
| |
| |
Did the Best Team Win? | |
| |
| |
The Big Question | |
| |
| |
Ability and Performance | |
| |
| |
Describing a Team's Ability | |
| |
| |
Describing a Team's Performance | |
| |
| |
Team Performance: 1871 to the Present | |
| |
| |
Explanations for the Winning Percentages | |
| |
| |
A Normal Curve Model | |
| |
| |
Team Performances over Time (Revisited) | |
| |
| |
A Mediocrity Model for Abilities | |
| |
| |
A Normal Model for Abilities | |
| |
| |
Weak, Average, and Strong Teams | |
| |
| |
A Model for Playing a Season | |
| |
| |
Simulating a Season | |
| |
| |
Simulating an American League Season | |
| |
| |
Simulating Many American League Seasons | |
| |
| |
Performances and Abilities of Different Types of Teams | |
| |
| |
Simulating an Entire Season | |
| |
| |
Chance | |
| |
| |
| |
Post-Game Comments (a Brief Afterword) | |
| |
| |
Bibliography | |