An Introduction to Statistical Learning


with Applications in R
Series: Springer Texts in Statistics, Vol. 103
James, G., Witten, D., Hastie, T., Tibshirani, R.

The stated purpose of this book is to facilitate the transition of statistical learning to mainstream. To achieve this the book has it’s own website  The website includes the R code for the book. The R package for the book is ISLR, which includes the data used in the book.

Introduction to Statistical learning does not replace Elements of Statistical Learning.  Instead it adds information by including more detail and R code to some of the topics in Elements of Statistical Learning.

The labs in the book are self contained and the code for them is on the website under the chapter headings.

Chapter 2.1.5 covers regression versus classification problems with good explanations  on what techniques to use for different types of data.

Good discussion on how use K-Nearest Neighbor, a non-parametric method.

Chapter 3.3.3 Potential Problems, covers common issues in fitting a linear regression model.

Chapter 7 covers splines in great detail. Then chapter 7 goes over Generalized Additive Models, GAM.

I am having a lot of fun playing with the code that goes with book.  I am glad that this was written.