Using multilinear regression

Simple linear regression, as seen in the previous recipe, is excellent for producing simple models of a relationship between one response variable and one predictor variable. Unfortunately, it is far more common to have a single response variable that depends on many predictor variables. Moreover, we might not know which variables from a collection make good predictor variables. For this task, we need multilinear regression.

In this recipe, we will learn how to use multilinear regression to explore the relationship between a response variable and several predictor variables.

Getting ready

For this recipe, we will need the NumPy package imported as np, the Matplotlib pyplot module imported as plt, the Pandas package imported as pd, and an instance of the NumPy default random number generator created using the following commands:

from numpy.random import default_rng
rng = default_rng(12345)

We will also need the statsmodels.api module imported...