Chapter 1, Getting Started with Regression, teaches by example why regression is useful for data science and how to quickly set up R for data science. We provide an overview of the packages used throughout the book.
Chapter 2, Basic Concepts – Simple Linear Regression, introduces regression with the simplest algorithm: simple linear regression. The chapter first describes a regression problem and where to fit a regressor, and then gives some intuitions underneath the math formulation.
Chapter 3, More Than Just One Predictor – MLR, shows how simple linear regression will be extended to extract predictive information from more than a feature. The stochastic gradient descent technique, explained in the previous chapter, will be scaled to cope with a vector of features.
Chapter 4, When the Response Falls into Two Categories – Logistic Regression, shows you how to approach classification and how to build a classifier that predicts class probability.
Chapter 5, Data Preparation Using R Tools, teaches you to properly parse a dataset, clean it, and create an output matrix optimally built for regression.
Chapter 6, Avoiding Overfitting Problems – Achieving Generalization, helps you avoid overfitting and create models with low bias and variance. Many techniques will be presented here to do so: stepwise selection and regularization (ridge, lasso, and elasticnet).
Chapter 7, Going Further with Regression Models, addresses the scaling problem, introducing a new set of techniques. We will learn how to scale linear models to a big dataset and how to deal with incremental data.
Chapter 8, Beyond Linearity – When Curving Is Much Better, applies advanced techniques to solve regression problems that cannot be solved with linear models.
Chapter 9, Regression Analysis in Practice, presents a series of applications where regression models can be successfully applied, allowing the reader to grasp possible applications for her/his own problems.
