Time Series Models for Business and Economic Forecasting

by Dick van Dijk, Anne Opschoor, Philip Hans Franses

Book Overview

Time Series Models for Business and Economic Forecasting is the most up-to-date and accessible guide to one of the fastest growing areas in business and economic analysis. The author is regarded as... This description may be from another edition of this product.

• Format: Paperback
• Language: English
• ISBN: 0521586410
• ISBN13: 9780521586412
• Release Date: November 1998
• Publisher: Cambridge University Press
• Length: 292 Pages
• Weight: 1.10 lbs.
• Dimensions: 0.7" x 6.0" x 8.9"

Customer Reviews

time series for business

To make this review short, I will say that I agree with all seven points made by the reviewer from New York, NY, whomever he or she may be. Franses is clear, concise, authoritative and up-to-date on all the advances. I particularly like the nice coverage of GARCH models that are new to me. It is a great introductory text especially for economics majors. For more advanced books and other treatments of time series consider Kennedy's fourth edition of "A Guide to Econometrics" or the suggestion from reviewer "New York, NY". Also my listmania list on time series will give you several sources to look at.

Good introductory book !

Full of real-life examples that provide some intuitive insight about the issues that may arise when modelling time series and forecasting. Requires some initial knowledge in statistics and algebra but if you're involved in time series modelling, it should be your first book. All the data thats used is available in the authors webbsite for downloading, very nice.

Excellent introductory book on economic time series modeling

Recently, I reread Franses book and expanded my review, which now includes 10 benefits.(1) Organization by key features of economic time series (trends, seasonality, outliers, conditional heteroskedasticity, non-linearity), rather than by methods, which provides a practical foundation for the various methodologies. The order in which chapters are presented reflects the order of difficulty in modeling trends, seasonality, etc. Even if there were no other benefits, this organization makes it worthwhile. (2) Appropriate level for first book on time series models as applied to economic time series, explaining more difficult concepts GARCH and VAR without excess detail. Box and Jenksins book is more a textbook; Brockwell and Davis is also more advanced; Hamilton is comprehensive and technical, but not as friendly. This book is very approachable even if you have had only 1 or 2 statistics courses. In economics, many people are interested in forecasting, and Franeses here is a good start. If you are looking for a more advanced forecasting book, try the recent books by Clements and Hendry from Cambridge U Press. (3) Clear distinction of the steps of model identification, estimation, diagnostics, and selection; something which other time series analysis books do not seem to do early or easily. (4) Delineates stochastic and deterministic models in the second chapter, providing a framework for when to take differences (eg. ARMA vs ARIMA). His timing is excellent. Many people I have interviewed on time series do not understand why they need to difference (eg use prices instead of returns) or why to transform the series (eg use logs instead of actual values).(5) Generous use of examples with real not simulated data with a website to download all the data, making it possible to import, graph, and analyze on your own. (6) A website containing printing corrections. Techincal books are likely to have some errors, but very few keep websites to list what those are.(7) Revealing graphics, especially for conditional heteroskedasticity, the 'CH' in GARCH. Figures 7.1-7.3 illustrate the concept that large returns tend to follow large returns very cleanly.(8) His notation is clear and consistent, yet not overwhelming: conventional Greek letters, only 1 level of subscripting, matrix noation where appropriate; even the results are neatly presented, as standard errors appear in () below their point estimates. Finally, Franses uses the same notation from chapter to chapter where the term is the same--not so common when chapters written by different authors.(9) Great appendices: extensive and updated references, a thorough subject index, and an author index. My only suggestion for improvement is that a second edition or the website should contain some exercises. Highly recommended.(10) The price! There are books published under Wiley at 3 to 4 times the price! under Springer Verlag for 2 to 3 times the price. Certain books are worth the money, but Cambridge U

Excellent introduction into time series

This book is a brilliant introduction into time series analysis. I found it a great basis for further analysis, allowing to go into deep with, for example, J.D. Hamilton's classical work. The book has a very well-defined structure, which (in my opinion) serves both auto-didact and (under)graduate teaching. Check out the author's web-page at Erasmus University Rotterdam for a list with corrections of some typos and the data sets used.

This book is exceptional

The beauty of this text is it's clarity and the author's choice to stay away from didactic lectures on formal statistical mathematics. I would highly recommend this book for anyone who has an undergraduate background in mathematics, statistics or economics and wants a medium level text to show them how to model time series.