Ulteriori informazioni
Zusatztext Whatever your preferences, there is valuable understanding to be gained by formulating these problems (or indeed any problem) in a Bayesian framework, and one of the strong points of this book is that it always looks for and often finds that understanding ... a valuable reference. Klappentext With an abundance of helpful examples, this text expertly presents the essentials of measurement, regression, and calibration. The book develops the fundamentals and underlying theories of key techniques in a clear, step-by-step progression, starting with standard least squares prediction of a single variable and moving on to shrinkage techniques for multiple variables. Self-contained chapters discuss methods that have been specifically developed for spectroscopy, likelihood and Bayesian inference (which may be applied to a wide range of multivariate regression problems), and Bayesian approaches to pattern recognition, among other topics. Ideal for instruction as well as for reference, Measurement, Regression, and Calibration will be a valuable addition to the bookshelves of professionals and advanced students in statistics and other pertinent fields. Zusammenfassung This book explains the statistical theory behind a range of regression problems in which one set of variables is predicted from another. The applications are from industry and medicine where the researchers are using sophisticated electronic measuring devices that are capable of monitoring very many variables. Inhaltsverzeichnis Introduction 1: Simple linear regression 2: Multiple regression and calibration 3: Regularized multiple regression 4: Multivariate calibration 5: Regession on curves 6: Non-linearity and selection 7: Pattern recognition A: Distribution theory B: Conditional inference C: Regularization dominance E: Partial least-squares algorithm Bibliography Index
