An Introduction to Statistical Learning: with Applications in R (Springer Texts in Statistics)

The authors Hastie and Tibshirani are legends in the stats world, creating GAM and LASSO respectively. Their other textbook "The Elements of Statistical Learning" is geared for PhD students. This textbook is very accessible, with figures and lots of sample code. The target audience is any aspiring data scientist who can learn to code and wants to actually understand what the code/models are doing (but doesn't need to be able to derive all the original math by hand). In addition to teaching different analyses, this book does a great job on explaining key statistical analysis concepts, like bias vs variance tradeoff, k-fold cross-validation, bootstrapping, finding the right balance in model complexity for your dataset, etc. There is both an R and a Python edition. The 2nd edition includes 3 new chapters on survival analysis, multiple testing, and neural nets. There is a free Stanford MOOC that uses this text.

I would like to upskill data related subject included introduction to statistics. Although I reached the beginning of chapter 3 but I've read and worked through all problems and exercises. Those are valuable although there are no solutions. I let gou recap and know in and out of R. But yes, you have to effort into it. Printings are in color. Paper is in good quality. Although thee cover slightly hit and bumped down a bit on the top left, I dont mind that much as it is a hard cover which protects paper inside. I believe after finish this one, I will continue the next in the series. In short, good purchase.

A true book for data analytics student.

I used this book in my statistical learning & data mining course last summer. At the time, the pdf version of this book was available from my university library so I didn't get the hard copy until now. The reason I decided to get the hard copy is that the theory/conceptual part is well-balanced between proper depth and easy-to-understand. Even though I'm now doing a Machine Learning training program in Python, I still recall the rationale of different models that were well explained in this book. So I've decided to get a permanent copy.

I wish they would discuss nonlinear regression vs GAM. Also better if they use caret in the R coding.

I recently used this book along with a couple others in a graduate level ML course. IMO it was the best in terms of striking a good balance; containing enough detail to help grasp theory but not so much that it becomes a slog to get through. I used the Ebook in class and liked it enough to buy a hardcopy. Unfortunately, the print font size is quite small. Overall dimension is smaller than listed on Amazon. Maybe that was how big the 1st edition was?

Trata los temas con claridad y de forma práctica

This book is an amazing resource to get your understanding across many different methods in line. One of the greatest tools of a data scientist and statistician in general is knowledge of best method, or best tool, for a task. Many solutions in data science right now go far too heavily toward one size fits all and this books helps one understand why knowing how to read your results and why to use the method to solve it really, really matter.

It was the same thing I ordered for

wonderfull book, I am currently studying a master in Bionformatics and needed to brush my forgotten lessons of Statistics. Amazed how the authors are able to explain the most advanced and difficult concepts skiping the mathematics below, for example the subject of hyperplanes is so amazingly exposed that it should be given as an role model of teaching and turning a difficult subject into an accesible one.I recommed this book with all my heart¡¡

The two professors in the video are the cutest old guy I have ever met!!!

I ordered a new book, but received a used book in bad shape instead!

I reviewed this book for a class in my master's program and I loved it from start to end. I already knew most of the concepts but became hooked because of how clear the explanations are. The authors convey complex ideas with remarkable simplicity, and for that, I think this is the most important book for data scientists. I am an avid opposer of the R programming language (ew) and even I enjoyed the applied programming parts of the book. In all honesty, the applications in R are very good, but it's not the main focus of the book. I think people should read this to understand the inner workings of the most popular AI algorithms instead of learning how to train predictive models (especially in R, haha). Overall, I think this is a great book for beginners and veterans alike. I would not hesitate to recommend this book to anyone interested in statistics, data and AI.