This report examines the relationship between field goal attempts
(GrAtt), game location (HomeIND, where
1 = Home and 0 = Away), and points scored
(GrPoint) using the Hoops dataset. Models are
evaluated using group equations, visual plots, and \(R^2\) values rather than p-values, t-tests,
or confidence intervals.
model1)model1 <- lm(GrPoint ~ GrAtt, data = my_data)
coef(model1)
ggplot(my_data, aes(x = GrAtt, y = GrPoint)) +
geom_point() +
geom_abline(intercept = coef(model1)[1], slope = coef(model1)[2]) +
labs(
title = "Grinnell Points vs. Field Goal Attempts (Single Line Model)",
x = "Field Goal Attempts (shots)",
y = "Points Scored (points)"
)
model1?
GrPoint (Points Scored) is the
response variable, and GrAtt (Field Goal Attempts) is the
explanatory variable.model2)model2 <- lm(GrPoint ~ GrAtt + HomeIND, data = my_data)
coef(model2)
ggplot(my_data, aes(x = GrAtt, y = GrPoint, color = factor(Home), shape = factor(Home))) +
geom_point() +
geom_abline(intercept = 25.7126233, slope = 0.9052887, color = "#F8766D") +
geom_abline(intercept = 35.2677201, slope = 0.9052887, color = "#00BFC4") +
labs(
title = "Grinnell Points vs. Field Goal Attempts (Parallel Lines Model)",
x = "Field Goal Attempts (shots)",
y = "Points Scored (points)",
color = "Home (1 = Home, 0 = Away)",
shape = "Home (1 = Home, 0 = Away)"
)
model2?
GrPoint is the response
variable, and GrAtt and HomeIND are the two
explanatory variables.(Intercept), GrAtt, and
HomeIND), and what are the intercept and slope for each
group’s line?
(Intercept): 25.7126233GrAtt: 0.9052887HomeIND: 9.5550968HomeIND = 0): \(\hat{y} = 25.7126233 + 0.9052887(\text{GrAtt}) +
9.5550968(0)\) \(\rightarrow\)
Intercept: 25.7126233,
Slope: 0.9052887HomeIND = 1): \(\hat{y} = (25.7126233 + 9.5550968) +
0.9052887(\text{GrAtt})\) \(\rightarrow\) Intercept:
35.2677201, Slope:
0.90528870.9052887) and the indicator coefficient
(9.5550968) in context, using the phrase “for two games
with the same…” in your explanations.
GrAtt slope): For two games
with the same location (both home or both away), each additional field
goal attempt is associated with an average increase of 0.91
points.HomeIND indicator): For two
games with the same number of field goal attempts, Grinnell is predicted
to score 9.56 more points on average in a home game than in
an away game.GrAtt = 100), and how does the difference between those
two predictions compare to the indicator coefficient?
HomeIND = 0): \(\widehat{\text{Points}} = 25.7126233 +
0.9052887(100) + 9.5550968(0) = 116.24\) points.HomeIND = 1): \(\widehat{\text{Points}} = 25.7126233 +
0.9052887(100) + 9.5550968(1) = 125.80\) points.9.5550968).
Because model2 is a parallel lines model, the vertical
distance between the two regression lines remains constant across all
values of field goal attempts.model3)my_data <- mutate(my_data, HomeINT = HomeIND * GrAtt)
model3 <- lm(GrPoint ~ GrAtt + HomeIND + HomeINT, data = my_data)
coef(model3)
ggplot(my_data, aes(x = GrAtt, y = GrPoint, color = factor(Home), shape = factor(Home))) +
geom_point() +
geom_abline(intercept = 21.94086592, slope = 0.94729430, color = "#F8766D") +
geom_abline(intercept = 38.69160661, slope = 0.86758618, color = "#00BFC4") +
labs(
title = "Grinnell Points vs. Field Goal Attempts (Interaction Model)",
x = "Field Goal Attempts (shots)",
y = "Points Scored (points)",
color = "Home (1 = Home, 0 = Away)",
shape = "Home (1 = Home, 0 = Away)"
)
model3?
GrPoint (Points Scored) is the
response variable, and GrAtt, HomeIND, and
HomeINT are the three explanatory variables.(Intercept), GrAtt, HomeIND, and
HomeINT), and what are the intercept and slope for each
group’s line?
(Intercept): 21.94086592GrAtt: 0.94729430HomeIND: 16.75074069HomeINT: -0.07970812HomeIND = 0): \(\hat{y} = 21.94086592 +
0.94729430(\text{GrAtt})\) \(\rightarrow\) Intercept:
21.94086592, Slope:
0.94729430HomeIND = 1): \(\hat{y} = (21.94086592 + 16.75074069) +
(0.94729430 - 0.07970812)(\text{GrAtt})\) \(\rightarrow\) Intercept:
38.69160661, Slope:
0.86758618-0.07970812) in context as the difference between the two
groups’ slopes.
GrAtt, predicted points increase by 0.07970812
points less for home games (0.8676 points/attempt) than for
away games (0.9473 points/attempt).summary(model1)$r.squared
summary(model2)$r.squared
summary(model3)$r.squared
model1, model2, and model3)?
model1 \(R^2\):
0.3787588model2 \(R^2\):
0.4383249model3 \(R^2\):
0.4390333model2 best captures the
relationship between field goal attempts, game location, and points
scored. Adding game location to field goal attempts increases \(R^2\) from 0.3788 to
0.4383, reflecting the clear upward shift seen for home
games on the graph. In contrast, moving to model3 by adding
the interaction term raises \(R^2\) by
a negligible 0.0007, confirming what the plots visually
show: the slopes for home and away games are nearly parallel, so a
shared slope with separate intercepts accurately captures the
relationship.