Applied Bayesian Forecasting and Time Series Analysis - Hardcover

Pole, Andy; West, Mike; Harrison, Jeff

Hardcover

ISBN 10: 0412044013 ISBN 13: 9780412044014

Publisher: Chapman and Hall/CRC, 1994

Synopsis

Practical in its approach, Applied Bayesian Forecasting and Time Series Analysis provides the theories, methods, and tools necessary for forecasting and the analysis of time series. The authors unify the concepts, model forms, and modeling requirements within the framework of the dynamic linear mode (DLM). They include a complete theoretical development of the DLM and illustrate each step with analysis of time series data. Using real data sets the authors: Explore diverse aspects of time series, including how to identify, structure, explain observed behavior, model structures and behaviors, and interpret analyses to make informed forecasts Illustrate concepts such as component decomposition, fundamental model forms including trends and cycles, and practical modeling requirements for routine change and unusual events Conduct all analyses in the BATS computer programs, furnishing online that program and the more than 50 data sets used in the text The result is a clear presentation of the Bayesian paradigm: quantified subjective judgements derived from selected models applied to time series observations. Accessible to undergraduates, this unique volume also offers complete guidelines valuable to researchers, practitioners, and advanced students in statistics, operations research, and engineering.

About this title

Review

"This book has filled a significant gap in the market for statistical texts. It should move Bayesian techniques for time series analysis and forecasting into the standard repertoire of applied statisticians. I think that it is an excellent book, and recommend it, especially to those who are not already familiar with these ideas." -The Statistician

Synopsis

This book discusses the practical forecasting and analysis of time series. It addresses the question of how to analyze time series data: how to identify structure, how to explain observed behavior, how to model those structures and behaviours, and how to use the insights gained from the analysis to make informed forecasts. Examination of real time series motivates concepts such as component decomposition, fundamental model forms such as trends and cycles, and practical modelling requirements such as dealing coherently with routine change and unusual events. The concepts, model forms, and modelling requirements are unified in the framework of the dynamic linear mode. A complete theoretical development of the DLM is presented, with each step along the way demonstrated with analysis of real time series. Inference is made within the Bayesian paradigm: quantified subjective judgements derived from selected models applied to time series observations. An integral part of the book is the BATS software program. BATS is supplied in both DOS and Windows versions. Completely menu driven, BATS provides all of the modelling facilities discussed and exemplified in the book.

Indeed, all the analyses in the book are performed with the program. There are also over 50 data sets in the book. Several are studied as detailed applications; several more are presented with preliminary analyses as starting points for detailed exercises. These data sets are included on the BATS diskette in the ASCII format. This book should be of interest to researchers, practitioners, and advanced students in statistic operations research and engineering.

Edition details

• Publisher: Chapman and Hall/CRC
• Publication date: 1994
• ISBN 10: 0412044013
• ISBN 13: 9780412044014
• Binding: Hardcover
• Language: English
• Edition number: 1
• Number of pages: 430