Chapter 16. Linear Models

The workhorse of statistical analysis is the linear model, particularly regression. Originally invented by Francis Galton to study the relationships between parents and children, which he described as regressing to the mean, it has become one of the most widely used modeling techniques and has spawned other models such as generalized linear models, regression trees, penalized regression and many others. In this chapter we focus on simple and multiple regression and some basic generalized linear models.

16.1. Simple Linear Regression

In its simplest form regression is used to determine the relationship between two variables. That is, given one variable, it tells us what we can expect from the other variable. This powerful ...

Get R for Everyone: Advanced Analytics and Graphics now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.