library(Stat2Data)
library(dplyr)
library(ggplot2)
Is a Porsche worth more than a Jaguar with the same mileage? Additionally, does one equation with an indicator variable (and maybe an interaction variable) predict better than a single line?
We begin by loading the PorscheJaguar dataset from the
Stat2Data package and plotting Price (in
thousands of dollars) against Mileage (in thousands of
miles), colored and shaped by Car (Jaguar vs. Porsche).
data("PorscheJaguar")
my_data <- PorscheJaguar
ggplot(my_data, aes(x = Mileage, y = Price, color = Car, shape = Car)) +
geom_point() +
labs(
title = "Price vs. Mileage for Porsches and Jaguars",
x = "Mileage (thousands of miles)",
y = "Price (thousands of dollars)"
)
In the scatterplot, the Porsche points sit noticeably higher than the Jaguar points. Both groups show a downward trend as mileage increases, and the steepness of their downward patterns looks roughly similar.
Next, we fit a single regression line (model1) ignoring
car brand:
model1 <- lm(Price ~ Mileage, data = my_data)
summary(model1)
##
## Call:
## lm(formula = Price ~ Mileage, data = my_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -33.088 -10.372 2.868 9.233 20.868
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 62.92843 3.16885 19.858 < 2e-16 ***
## Mileage -0.61269 0.07621 -8.039 5.26e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 12.89 on 58 degrees of freedom
## Multiple R-squared: 0.527, Adjusted R-squared: 0.5189
## F-statistic: 64.63 on 1 and 58 DF, p-value: 5.263e-11
For model1, the R-squared is 0.527 and
the residual standard error is 12.89 thousand
dollars.
PorscheIND)To account for the difference in price between the two car brands, we
create an indicator variable PorscheIND that equals
1 for a Porsche and 0 for a Jaguar, and fit
model2 with both Mileage and
PorscheIND.
my_data <- mutate(my_data, PorscheIND = ifelse(Car == "Porsche", 1, 0))
my_data %>%
select(Mileage, Price, Car, PorscheIND) %>%
head()
## Mileage Price Car PorscheIND
## 1 21.5 69.4 Porsche 1
## 2 43.0 56.9 Porsche 1
## 3 19.9 49.9 Porsche 1
## 4 36.0 47.4 Porsche 1
## 5 44.0 42.9 Porsche 1
## 6 49.8 36.9 Porsche 1
model2 <- lm(Price ~ Mileage + PorscheIND, data = my_data)
coef(model2)
## (Intercept) Mileage PorscheIND
## 53.605550 -0.602977 17.958331
From the model coefficients ((Intercept) =
53.605550, Mileage =
-0.602977, and PorscheIND =
17.958331), we obtain two parallel lines—one for each
brand:
PorscheIND = 0): \(\widehat{\text{Price}} = 53.605550 -
0.602977(\text{Mileage})\)PorscheIND = 1): \(\widehat{\text{Price}} = 71.563881 -
0.602977(\text{Mileage})\)ggplot(my_data, aes(x = Mileage, y = Price, color = Car, shape = Car)) +
geom_point() +
geom_abline(intercept = 53.605550, slope = -0.602977, color = "#F8766D") +
geom_abline(intercept = 71.563881, slope = -0.602977, color = "#00BFC4") +
labs(
title = "Price vs. Mileage with Parallel Lines (Model 2)",
x = "Mileage (thousands of miles)",
y = "Price (thousands of dollars)"
)
PorscheIND (17.958331):
For two cars with the same mileage, a Porsche is predicted to cost
17.958331 thousand dollars more on average than a
Jaguar.Mileage (-0.602977): For
two cars of the same brand, as mileage increases by 1 thousand miles,
predicted price decreases by 0.602977 thousand dollars
on average.Mileage = 30 (30,000
miles):
PorscheIND coefficient because the two regression lines are
parallel.PorscheINT)To test whether Porsches and Jaguars depreciate at different rates
per mile, we create an interaction variable
PorscheINT = PorscheIND * Mileage and fit
model3.
my_data <- mutate(my_data, PorscheINT = PorscheIND * Mileage)
model3 <- lm(Price ~ Mileage + PorscheIND + PorscheINT, data = my_data)
coef(model3)
## (Intercept) Mileage PorscheIND PorscheINT
## 54.22746396 -0.62029888 16.86298877 0.03089793
Using the four coefficients ((Intercept) =
54.22746396, Mileage =
-0.62029888, PorscheIND =
16.86298877, and PorscheINT =
0.03089793), each group’s line has its own intercept
and slope:
PorscheIND = 0): \(\widehat{\text{Price}} = 54.22746396 -
0.62029888(\text{Mileage})\)PorscheIND = 1): \(\widehat{\text{Price}} = 71.09045273 -
0.58940095(\text{Mileage})\)ggplot(my_data, aes(x = Mileage, y = Price, color = Car, shape = Car)) +
geom_point() +
geom_abline(intercept = 54.22746396, slope = -0.62029888, color = "#F8766D") +
geom_abline(intercept = 71.09045273, slope = -0.58940095, color = "#00BFC4") +
labs(
title = "Price vs. Mileage with Interaction Lines (Model 3)",
x = "Mileage (thousands of miles)",
y = "Price (thousands of dollars)"
)
PorscheINT (0.03089793):
The slope of predicted price on mileage is 0.03089793
thousand dollars per thousand miles higher (less steep) for Porsches
than for Jaguars—meaning that for each additional 1 thousand miles, a
Porsche’s predicted price drops by 0.03089793 thousand
dollars less on average than a Jaguar’s.Finally, we inspect the summaries of model2 and
model3 to compare their fit with model1.
summary(model2)
##
## Call:
## lm(formula = Price ~ Mileage + PorscheIND, data = my_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -23.8420 -5.6835 -0.5041 5.4209 19.3490
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 53.60555 2.56951 20.862 < 2e-16 ***
## Mileage -0.60298 0.05427 -11.111 6.89e-16 ***
## PorscheIND 17.95833 2.36951 7.579 3.45e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.174 on 57 degrees of freedom
## Multiple R-squared: 0.7644, Adjusted R-squared: 0.7562
## F-statistic: 92.48 on 2 and 57 DF, p-value: < 2.2e-16
summary(model3)
##
## Call:
## lm(formula = Price ~ Mileage + PorscheIND + PorscheINT, data = my_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -24.3271 -5.6200 -0.4819 5.0278 18.8120
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 54.22746 3.41097 15.898 < 2e-16 ***
## Mileage -0.62030 0.08254 -7.515 4.88e-10 ***
## PorscheIND 16.86299 4.58044 3.682 0.000523 ***
## PorscheINT 0.03090 0.11024 0.280 0.780302
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.25 on 56 degrees of freedom
## Multiple R-squared: 0.7648, Adjusted R-squared: 0.7522
## F-statistic: 60.68 on 3 and 56 DF, p-value: < 2.2e-16
model1 (Single Line): R-squared =
0.527, Residual Standard Error = 12.89
thousand dollarsmodel2 (Indicator / Parallel Lines):
R-squared = 0.7644, Residual Standard Error =
9.174 thousand dollarsmodel3 (Indicator + Interaction):
R-squared = 0.7648, Residual Standard Error =
9.25 thousand dollarsAdding the indicator variable in model2 dramatically
improved the fit compared to a single line—R-squared jumped from
0.527 to 0.7644, and the residual
standard error dropped from 12.89 to
9.174 thousand dollars. In contrast, adding the
interaction variable in model3 added almost nothing
(R-squared barely changed from 0.7644 to
0.7648, while the residual standard error slightly
worsened to 9.25 thousand dollars). Therefore,
model2 is the best model.
Answer to the Research Question: Yes, a Porsche is worth more than a Jaguar with the same mileage—specifically, 17.958331 thousand dollars more on average.