ECON 375: Module 3 Homework
Respond to each of the following questions in a Word document. Number your responses to match the questions.
Submit your document on Canvas. Points possible = 24.
Data file: “Baseball.xlsx”
. These data include attendance for all minor league baseball teams in the year 2022
along market data and other data related to each individual team. Variable descriptions are included in the second
sheet.
1. Minor league baseball has four levels, from lowest to highest in terms of baseball skill: A, A+, AA, and AAA.
(a)
R
Provide the density distributions of attendance, conditional on the level, in the same graph. Make
sure the full distributions of each are visible! (2 points)
(b)
R
Instead of showing the entire distributions, compute the means of attendance conditional on level,
and provide this in a table. (2 points)
2.
R
Make a scatter plot that shows the relationship between
stadium
age
(on the x axis) and
attendance
(on
the y axis). Include a linear regression line. Justify why each variable is on that axis and not the other way
around. (4 points)
3. Write the linear regression model you are estimating, with
attendance
as the dependent variable and
stadium
age
as the x variable. Use subscripts and greek letters appropriately. (3 points)
4.
R
Use OLS to estimate the linear regression model. List your estimated
ˆ
β
0
and
ˆ
β
1
. Round your answers to
1 decimal place. (2 points)
(Link: How to put hats over Greek letters in Word)
5.
R
List the
R
2
value of your regression. Interpret what that value means in words. (2 points)
6. Interpret each of your estimates in words. Be careful with your wording! (2 points)
7. Calculate the residual for the Springfield Cardinals. Show your work for how you found this number. Explain
what that number means in words. (3 points)
8. Suppose a new minor league baseball team, the Bayou Voodoo, begins playing in Baton Rouge, Louisiana. In
its first season, their stadium will be 14 years old. According to your model, what is the Voodoo’s expected
average attendance, given its stadium age? If the Voodoo play 70 home games in their first season and their
average ticket price is
$
8, how much ticket revenue would they be expecting to collect over the year? (2 points)
9. Suggest one reason why
ˆ
β
1
is not likely to be a causal effect of a stadium aging by 1 year. In other words,
why might the
ˆ
β
1
you found be biased. Your explanation should include some reference to this data / research
question. (2 points)
10.
R
Extra Credit:
Regress attendance on market population, but use market population on a log scale.
Justify why market population should be on a log scale. Correctly interpret the slope coefficient that you find.
(2 points)
Questions labeled
R
must be answered using R. I should be able to download your script file, drop it into my project
with the data, and run the code to generate your answers to these questions. Correct answers without corresponding
code used to generate those answers are given half credit.
1
