Statistical Analysis Techniques in Particle Physics – Fits, Density Estimation and Supervised Learning FIRST, DENSITY ESTIMATION AND SUPERVISED LEARNING

Modern analysis of physics data often relies on advanced techniques for separation of signal and background. Usually this involves some machine learning technique, which is the focus of this book. By means of analysis examples it is shown how observables are extracted from data, how signal and background are estimated and how accurate error estimates are obtained exploiting uni- and multivariate analysis techniques, such as non-parametric density estimation, likelihood fits, neural networks, support vector machines, decision trees, ensembles of classifiers etc. The book includes simple code snippets which depend on software suites such as Root, Matlab, or specific machine learning packages such as StatPatternRecognition. These snippets either include codes for generating data or use public data downloadable off the web. The book is intended for study and research. The material is partially based on lecture series by the authors at the Stanford National Accelerator Laboratory, at Caltech, and the BaBar Analysis School.

Modern analysis of HEP data needs advanced statistical tools to separate signal from background. This is the first book which focuses on machine learning techniques. It will be of interest to almost every high energy physicist, and, due to its coverage, suitable for students.