Two numeric explanatory variables

Intermediate Regression in R

Richie Cotton

Data Evangelist at DataCamp

Visualizing 3 numeric variables

3D scatter plot
2D scatter plot with response as color

Another column for the fish dataset

species	mass_g	length_cm	height_cm
Bream	1000	33.5	18.96
Bream	925	36.2	18.75
Roach	290	24.0	8.88
Roach	390	29.5	9.48
Perch	1100	39.0	12.80
Perch	1000	40.2	12.60
Pike	1250	52.0	10.69
Pike	1650	59.0	10.81

3D scatter plot

library(plot3D)

scatter3D(fish$length_cm, fish$height_cm, fish$mass_g)

library(plot3D)
library(magrittr)

fish %$%
  scatter3D(length_cm, height_cm, mass_g)

3D scatter plot

library(plot3D)
library(magrittr)

fish %$%
  scatter3D(length_cm, height_cm, mass_g)

2D scatter plot, color for response

ggplot(
  fish, 
  aes(length_cm, height_cm, color = mass_g)
) +
  geom_point()

Viridis color scales

ggplot(
  fish, 
  aes(length_cm, height_cm, color = mass_g)
) +
  geom_point() +
  scale_color_viridis_c(option = "inferno")

Modeling with 2 numeric explanatory variables

mdl_mass_vs_both <- lm(mass_g ~ length_cm + height_cm, data = fish)

Call:
lm(formula = mass_g ~ length_cm + height_cm, data = fish)

Coefficients:
(Intercept)    length_cm    height_cm  
    -622.16        28.97        26.34

The prediction flow

explanatory_data <- expand_grid(
  length_cm = seq(5, 60, 5),
  height_cm = seq(2, 20, 2)
)

prediction_data <- explanatory_data %>% 
  mutate(
    mass_g = predict(mdl_mass_vs_both, explanatory_data)
  )

Plotting the predictions

ggplot(
  fish, 
  aes(length_cm, height_cm, color = mass_g)
) +
  geom_point() +
  scale_color_viridis_c(option = "inferno") +
  geom_point(
    data = prediction_data, shape = 15, size = 3
  )

Including an interaction

mdl_mass_vs_both_inter <- lm(mass_g ~ length_cm * height_cm, data = fish)

Call:
lm(formula = mass_g ~ length_cm * height_cm, data = fish)

Coefficients:
        (Intercept)            length_cm            height_cm  length_cm:height_cm  
           159.1144               0.3001             -78.1234               3.5455

The prediction flow again

explanatory_data <- expand_grid(
  length_cm = seq(5, 60, 5),
  height_cm = seq(2, 20, 2)
)

prediction_data <- explanatory_data %>% 
  mutate(
    mass_g = predict(mdl_mass_vs_both_inter, explanatory_data)
  )

Plotting the predictions

ggplot(
  fish, 
  aes(length_cm, height_cm, color = mass_g)
) +
  geom_point() +
  scale_color_viridis_c(option = "inferno") +
  geom_point(
    data = prediction_data, shape = 15, size = 3
  )

scatter-color-fish-length-height-mass-inferno-pred-inter.png

Let's practice!

Intermediate Regression in R