Overview

This report evaluates three linear regression models to predict vehicle Price (in thousands of dollars) from Mileage (in thousands of miles) across two car brands (Jaguar and Porsche):

  1. Model 1 (Single Line): Predicts Price using only Mileage.
  2. Model 2 (Parallel Lines): Adds an indicator variable (PorscheIND) to allow different intercepts by brand while keeping a common slope.
  3. Model 3 (Interaction): Adds an interaction term (PorscheINT) to allow both different intercepts and different slopes by brand.

Step 1: Baseline Model (Single Line)

model1 <- lm(Price ~ Mileage, data = my_data)
coef(model1)
## (Intercept)     Mileage 
##  62.9284289  -0.6126897
ggplot(my_data, aes(x = Mileage, y = Price, color = Car, shape = Car)) +
  geom_point() +
  geom_abline(intercept = coef(model1)[1], slope = coef(model1)[2]) +
  labs(
    title = "Price vs. Mileage (Single Regression Line)",
    x = "Mileage (thousands of miles)",
    y = "Price (thousands of dollars)"
  )


Step 2: Parallel Lines Model (Indicator Variable)

We create PorscheIND (1 for Porsche, 0 for Jaguar) and fit model2.

my_data <- mutate(my_data, PorscheIND = ifelse(Car == "Porsche", 1, 0))

model2 <- lm(Price ~ Mileage + PorscheIND, data = my_data)
coef(model2)
## (Intercept)     Mileage  PorscheIND 
##   53.605550   -0.602977   17.958331

Group Equations & Predictions at 30,000 Miles (Mileage = 30)

  • Jaguar (PorscheIND = 0): \(\widehat{\text{Price}} = 53.6057 - 0.60298 \times \text{Mileage}\)
    • At Mileage = 30: $35,516.24
  • Porsche (PorscheIND = 1): \(\widehat{\text{Price}} = 71.5640 - 0.60298 \times \text{Mileage}\)
    • At Mileage = 30: $53,474.57

Coefficient Interpretations

  • PorscheIND (17.958331): For two cars with the same mileage, a Porsche is predicted to cost $17,958.33 more than a Jaguar, on average. Because the lines are parallel, the difference between predicted prices at any mileage is always equal to this coefficient.
  • Mileage (-0.602982): For two cars of the same brand, every additional 1,000 miles decreases the predicted price by approximately $602.98, on average.
ggplot(my_data, aes(x = Mileage, y = Price, color = Car, shape = Car)) +
  geom_point() +
  geom_abline(intercept = 53.605704, slope = -0.602982, color = "#F8766D") +
  geom_abline(intercept = 71.564035, slope = -0.602982, color = "#00BFC4") +
  labs(
    title = "Price vs. Mileage by Car Brand (Parallel Lines Model)",
    x = "Mileage (thousands of miles)",
    y = "Price (thousands of dollars)"
  )


Step 3: Interaction Model (Different Slopes)

We create the 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

Group Equations & Slope Difference

  • Jaguar (PorscheIND = 0, PorscheINT = 0): Intercept = 54.22746396, Slope = -0.62029888
  • Porsche (PorscheIND = 1, PorscheINT = Mileage): Intercept = 71.09045273, Slope = -0.58940095
  • PorscheINT (0.03089793): For every additional 1,000 miles, the predicted