Elements of Statistical Learning: Data Mining, Inference, Prediction, 2nd Edition

In a common conceptual framework, this book delineates significant ideas in various fields like medicine, biology, finance, and marketing. Although the approach is statistical, the focal point is on concepts rather than mathematics. Numerous examples are provided, accompanied by vivid color graphics. It serves as a valuable resource for statisticians and individuals keen on data mining in science or industry. The book covers a wide range of topics, from supervised learning (prediction) to unsupervised learning. The plethora of topics includes neural networks, support vector machines, classification trees, and boosting - marking the first comprehensive treatment of this subject in any book.

This updated edition introduces several new topics that were not previously covered, such as graphical models, random forests, ensemble methods, least angle regression & path algorithms for the lasso, non-negative matrix factorization, and spectral clustering. Additionally, there is a section dedicated to techniques for "wide'' data (p greater than n), including multiple testing and false discovery rates.

product information: