What is a better predictor of the number of wins for a baseball team, the number of runs scored by the team or the number of runs they allow the other team to score? What variables can we use to predict the number of runs a team scores? To predict the number of runs it allows the other team to score? In this project, you will use technology to help answer these questions by exploring a large set of data from Major League Baseball.

Part 1

1. Download the “MLB Team Data 2012–2016” Excel file from the book’s website, along with the “Glossary for MLB Team Data file,” which explains each of the variables included in the data set.44 Import the data into the statistical software package you prefer.

2. Create a scatterplot to investigate the relationship between runs scored per game (R/G) and wins (W). Then calculate the equation of the least-squares regression line, the standard deviation of the residuals, and r². Note: R/G is in the section for hitting statistics and W is in the section for pitching statistics.

3. Create a scatterplot to investigate the relationship between runs allowed per game (RA/G) and wins (W). Then calculate the equation of the least-squares regression line, the standard deviation of the residuals, and r². Note: Both of these variables may be found in the section for pitching statistics.

4. Compare the two associations. Is runs scored or runs allowed a better predictor of wins? Explain your reasoning.

5. Because the number of wins a team has is dependent on both how many runs they score and how many runs they allow, we can use a combination of both variables to predict the number of wins. Add a column in your data table for a new variable, run differential. Fill in the values using the formula R/G – RA/G.

6. Create a scatterplot to investigate the relationship between run differential and wins. Then calculate the equation of the least-squares regression line, the standard deviation of the residuals, and r².

7. Is run differential a better predictor than the variable you chose in Question 4? Explain your reasoning.

Part 2

It is fairly clear that the number of games a team wins is dependent on both runs scored and runs allowed. But what variables help predict runs scored? Runs allowed?

1. Choose either runs scored (R) or runs allowed (RA) as the response variable you will try to model.

2. Choose at least three different explanatory variables (or combinations of explanatory variables) that might help predict the response variable you chose in Question 1. Create a scatterplot using each explanatory variable. Then calculate the equation of the least-squares regression line, the standard deviation of the residuals, and r² for each relationship.

3. Which explanatory variable from Question 2 is the best? Explain your reasoning.