I’m excited to be writing this book review. It is a book for which I’ve been waiting a long time. An Introduction to Statistical Learning with Application in R by James, Witten, Hastie, and Tibshirani is a contemporary re-work of the classic machine learning text Elements of Statistical Learning by Hastie, Tibshirani, and Friedman. This book has been front and center on my research bookshelf for years. My familiarity with it comes from the Stanford University graduate program in computer science and mathematical statistics (in dated nomenclature, “data mining”). The book excels in providing the theoretical and mathematical basis for machine learning, and now at long last, a practical view with the inclusion of R programming examples. It is the latter portion of the update that I’ve been waiting for as it directly applies to my work in data science. Give the new state of this book, I’d classify it as the authoritative text for any machine learning practitioner.
The book contains clear and concise material for an introduction to statistical learning – linear regression, classification, resampling methods including The Bootstrap, model selection with regularization, non-linear models, tree-based methods, support vector machines and unsupervised learning including principal component analysis and clustering. This is one book you need to get if you’re serious about this growing field.
You can download the last revision of the previous edition for free HERE (pdf).