Jorma Rissanen

eBook, PDF

Information and Complexity in Statistical Modeling (eBook, PDF)

Beschreibung

This volume presents a different, yet logically unassailable, view of statistical modeling. It details a method of modeling based on the principle that the objective is to extract the information from data that can be learned with suggested classes of probability models. The intuitive and fundamental concepts of complexity, learnable information, and noise are formalized, which provides a firm information theoretic foundation for statistical modeling. The view of the modeling problem presented in this book permits a unified treatment of any type of parameters, their number, and even their structure. Since only optimally distinguished models are worthy of testing, a logically sound and straightforward treatment of hypothesis testing is found in which the confidence in the test result can be assessed. The techniques presented in this book have application in all fields of modern engineering, including signal and image processing, bioinformatics, pattern recognition, and machine learning.

Technische Details

• Geräte: PC
• ohne Kopierschutz
• Größe: 5.94MB

Barrierefreiheit

• Text-to-Speech

Produktdetails

• Verlag: Springer US
• Seitenzahl: 142
• Erscheinungstermin: 15. Dezember 2007
• Englisch
• ISBN-13: 9780387688121
• Artikelnr.: 37287969

Rezensionen

From the reviews:

"Readership: Graduate students and researchers in statistics, computer science and engineering, anyone interested in statistical modelling. This book presents a personal introduction to statistical modelling based on the principle that the objective of modelling is to extract learnable information from data with suggested classes of probability models. It grew from lectures to doctoral students ... and retains much of the economical style of a lecture series. ... Therefore, this fascinating volume offers an excellent source of important statistical research problems calling for solution." (Erkki P. Liski, International Statistical Review, Vol. 75 (2), 2007)

"This book covers the minimum description length

(MDL) principle ... . For statistics beginners, this book is self-contained. The writing style is concise ... . Overall, this is an authoritative source on MDL and a good reference book. Most statisticians would be fortunate to have a copy in their bookshelves." (Thomas C. M. Lee, Journal of the American Statistical Association, Vol. 103 (483), September, 2008)

"This book describes the latest developments of the MDL principle. ... The book ... is intended to serve as a readable introduction to the mathematical aspects of the MDL principle when applied to statistical modeling for graduate students in statistics and information sciences. ... Overall, this interesting book will make an important contribution to the field of statistical modeling through the MDL principle." (Prasanna Sahoo, Zentralblatt Math, Vol. 1156, 2009)