Time-Series Forecasting

ISBN-13: 9781584880639 / Angielski / Twarda / 2000 / 280 str.

Christopher Chatfield

Opis

From the author of the bestselling "Analysis of Time Series," Time-Series Forecasting offers a comprehensive, up-to-date review of forecasting methods. It provides a summary of time-series modelling procedures, followed by a brief catalogue of many different time-series forecasting methods, ranging from ad-hoc methods through ARIMA and state-space modelling to multivariate methods and including recent arrivals, such as GARCH models, neural networks, and cointegrated models.
The author compares the more important methods in terms of their theoretical inter-relationships and their practical merits. He also considers two other general forecasting topics that have been somewhat neglected in the literature: the computation of prediction intervals and the effect of model uncertainty on forecast accuracy.
Although the search for a "best" method continues, it is now well established that no single method will outperform all other methods in all situations-the context is crucial. Time-Series Forecasting provides an outstanding reference source for the more generally applicable methods particularly useful to researchers and practitioners in forecasting in the areas of economics, government, industry, and commerce.

Recenzje

"The combination of the author's deep and extensive knowledge of the mathematics of time series, his pragmatic approach, and his clear writing style mean that the book is pretty close to being a time-series forecasting masterpiece."
-International Journal of Forecasting, 2003

"This book is a wide-ranging and yet concise, practical guide to the use of time-series modelling in forecasting. … the author describes models in an engaging and concise way. … refreshingly concise. … [the author's] views are persuasively put, with evidence and references to back them up. If you are willing to be challenged about your current methodology and thinking, this book will be invaluable."
-Journal of the Operational Research Society, 2003

"This well-written and comprehensive review of current time-series and forecasting methods should quickly earn a place among standard reference materials. … It presents these methods from a utilitarian perspective, clearly explaining what these methods may potentially accomplish and what risks they entail. Brief summaries explain the related theory in plain prose. Numerous references direct the interested reader to more information on specific details and tangents, theoretical results, and special applications. … One of the book's strengths is that after presenting a topic, the author routinely brings his personal views and experiences into the picture. Another strength is the numerous checklists of ideas throughout, which serve to clarify concepts and reinforce key points that are easy to forget. The author's advice comes across as thoughtful guidance, and makes this book more interesting to read. … In summary, this book represents a helpful and enlightening reference for practicing statisticians…who work with time series and forecasting applications and who wish to think critically about current practice in these areas. The book could also be the core text of a graduate seminar on forecasting for students with a good background in time series analysis."
-Technometrics, May 2002, vol. 44 NO. 2

"…provides a reasonably self-contained treatment of forecasting, based on time-series analysis…provides a good overview of the main relevant theoretical developments without going into details…useful reference for practitioners and researchers in areas such as economics or management science, where time-series data naturally occur. Readers wanting to get a more detailed idea of some of these areas will find the list of references quite extensive and up-to-date.
-M. Steel, Institute of Mathematics and Statistics, University of Kent at Canterbury, Canterbury, UK

"… the book provides a good overview of the main relevant theoretical developments without going into details. … a useful reference for practitioners and researchers in areas such as economics or management science … list of references quite extensive and up-to-date … useful for a graduate course on the topic … the book is designed as a reference source for practitioners and researchers with interests in this field, and I think it achieves that goal quite well."
Biometrics, Vol. 57, No. 2, June 2001

"However, the value of this book is... the way it draws our attention to recent work, and the sections devoted to comparing the methods and making recommendations as to their merits and application."
-Short Book Reviews of the ISI, vol.21, no.3, December 2001

Spis treści

INTRODUCTION
Types of Forecasting Methods
Some Preliminary Questions
The Dangers of Extrapolation
Are Forecasts Genuinely Out-of-Sample?
Brief Overview of Relevant Literature
BASICS OF TIME-SERIES ANALYSIS
Different Types of Time Series
Objectives of Time-Series Analysis
Simple Descriptive Techniques
Stationary Stochastic Processes
Some Classes of Univariate Time-Series Models
The Correlogram
UNIVARIATE TIME-SEIES MODELLING
ARIMA Models and Related Topics
State Space Models
Growth Curve Models
Nonlinear Models
Time-Series Model Building
UNIVARIATE FORECASTING METHODS
The Prediction Problem
Model-Based Forecasting
Ad Hoc Forecasting Methods
Some Interrelationships and Combinations
MULTIVARIATE FORECASTING METHODS
Introduction
Single-Equation Models
Vector AR and ARMA Models
Cointegration
Econometric models
Other Approaches
Some Relationships Between Models
A COMPARATIVE ASSESSMENT OF FORECASTING METHODS
Introduction
Criteria for Choosing a Forecasting Method
Measuring Forecast Accuracy
Forecasting Competitions and Case Studies
Choosing an Appropriate Forecasting Method
Summary
CALCULATING INTERVAL FORECASTS
Introduction
Notation
The Need for Different Approaches
Expected Mean Square Prediction Error
Procedures for Calculating P.I.s
A Comparative Assessment
Why are P.I.s too Narrow?
An Example
Summary and Recommendations
MODEL UNCERTAINTY AND FORECAST ACCURACY
Introduction to Model Uncertainty
Model Building and Data Dredging
Examples
Inference after Model Selection: Some Findings
Coping with Model Uncertainty
Summary and Discussion
REFERENCES

O autorze

Chris Chatfield