Chapter 7: Linear Regression Models

Linear regression is perhaps the most well-known machine learning algorithm, having origins in statistical learning at least 200 years ago. If you took a statistics, econometrics, or psychometrics course in college, you were likely introduced to linear regression, even if you took that course long before machine learning was taught in undergraduate courses. As it turns out, many social and physical phenomena can be successfully modeled as a function of a linear combination of predictor variables. This is as useful for machine learning as it has been for statistical learning all these years, though, with machine learning, we care much less about the parameter values than we do about predictions.

Linear regression is a very good choice for modeling a continuous target, assuming that our features and target have certain qualities. In this chapter, we will go over the assumptions of linear regression models and construct a model using data that is...