In the previous three chapters, we introduced the fundamental ideas behind machine learning, the statistical modeling tool that we utilize in this text (R and RStudio), and how to manage data for the machine learning process. In this chapter, we introduce the first of the supervised machine learning approaches we cover in this book. It is an approach that is used to generate a numeric prediction in situations when we want to answer questions such as the amount of revenue that would be generated by a potential customer based on the type and amount of money spent on advertising, the number of bicycles that might be rented on a particular day based on weather patterns, or the blood pressure of a particular patient based on other characteristics. This approach is known as regression.
Regression techniques are a category of machine learning algorithms that seek to predict a numeric response by quantifying the size and strength of the relationship between numerical values. In this chapter, we introduce linear regression as a supervised learning method that attempts to use the observed data to fit a linear predictor function that estimates unobserved data.
By the end of this chapter, you will have learned the following:
- The underlying statistical principles behind simple and multiple linear regression
- How to fit a simple linear regression model using R
- How to evaluate, interpret, and apply the results of a simple linear regression model
- How to extend the ...