- Series: Use R!
- Paperback: 272 pages
- Publisher: Springer; 2009 edition (June 9, 2009)
- Language: English
- ISBN-10: 0387886974
- ISBN-13: 978-0387886978
- Product Dimensions: 6.1 x 0.6 x 9.2 inches
- Shipping Weight: 1 pounds (View shipping rates and policies)
- Average Customer Review: 35 customer reviews
- Amazon Best Sellers Rank: #73,522 in Books (See Top 100 in Books)
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
Introductory Time Series with R (Use R!) 2009th Edition
Use the Amazon App to scan ISBNs and compare prices.
Frequently bought together
Customers who bought this item also bought
From the reviews:
“The book…gives a very broad and practical overview of the most common models for time series analysis in the time domain and in the frequency domain, with emphasis on how to implement them with base R and existing R packages such as Rnlme, MASS, tseries, fracdiff, mvtnorm, vars, and sspir. The authors explain the models by first giving a basic theoretical introduction followed by simulation of data from a particular model and fitting the latter to the simulated data to recover the parameters. After that, they fit the class of models to either environmental, finance, economics, or physics data. There are many applications to climate change and oceanography. The R programs for the simulations are given even if there are R functions that would do the simulation. All examples given can be reproduced by the reader using the code provided…in all chapters. Exercises at the end of each chapter are interesting, involving simulation, estimation, description, graphical analysis, and some theory. Data sets used throughout the book are available in a web site or come with base R or the R packages used. The book is a great guide to those wishing to get a basic introduction to modern time series modeling in practice, and in a short amount of time. …” (Journal of Statistical Software, January 2010, Vol. 32, Book Review 4)
“Later year undergraduates, beginning graduate students, and researchers and graduate students in any discipline needing to explore and analyse time series data. This very readable text covers a wide range of time series topics, always however within a theoretical framework that makes normality assumptions. The range of models that are discussed is unusually wide for an introductory text. … The mathematical theory is remarkably complete … . This text is recommended for its wide-ranging and insightful coverage of time series theory and practice.” (John H. Maindonald, International Statistical Review, Vol. 78 (3), 2010)
“The authors present a textbook for students and applied researchers for time series analysis and linear regression analysis using R as the programming and command language. … The book is written for students with knowledge of a first-year university statistics course in New-Zealand and Australia, but it also might serve as a useful tools for applied researchers interested in empirical procedures and applications which are not menu driven as it is the case for most econometric software packages nowadays.” (Herbert S. Buscher, Zentralblatt MATH, Vol. 1179, 2010)
From the Back Cover
Yearly global mean temperature and ocean levels, daily share prices, and the signals transmitted back to Earth by the Voyager space craft are all examples of sequential observations over time known as time series. This book gives you a step-by-step introduction to analysing time series using the open source software R. Each time series model is motivated with practical applications, and is defined in mathematical notation. Once the model has been introduced it is used to generate synthetic data, using R code, and these generated data are then used to estimate its parameters. This sequence enhances understanding of both the time series model and the R function used to fit the model to data. Finally, the model is used to analyse observed data taken from a practical application. By using R, the whole procedure can be reproduced by the reader. All the data sets used in the book are available on the website http://staff.elena.aut.ac.nz/Paul-Cowpertwait/ts/.
The book is written for undergraduate students of mathematics, economics, business and finance, geography, engineering and related disciplines, and postgraduate students who may need to analyse time series as part of their taught programme or their research.
Paul Cowpertwait is an associate professor in mathematical sciences (analytics) at Auckland University of Technology with a substantial research record in both the theory and applications of time series and stochastic models. Andrew Metcalfe is an associate professor in the School of Mathematical Sciences at the University of Adelaide, and an author of six statistics text books and numerous research papers. Both authors have extensive experience of teaching time series to students at all levels.
Try the Kindle edition and experience these great reading features:
Showing 1-8 of 35 reviews
There was a problem filtering reviews right now. Please try again later.
First, some good points:
1. If you have no prior experience with R, the book gives you some useful tidbits and you can use the code to jump start various analyses.
2. Most of the book consists of sections that are stand-alone resources, so if there is a topic of particular interest, such as spectral analysis, you can go to that section and get useful advice.
3. The problems at the end of each section are very helpful, and an answer file is available via a simple internet search.
4. Most of the code works, but the link to the data is old - a simple internet search yields the current link.
5. Chapter 3 (Holt Winters) was interesting and useful.
6. The breadth of the book is quite good, but for each topic, there is absolutely no depth, which yields numerous additional problems….
1. Detailed descriptions of important concepts are lacking, and explanations are shallow. For example, the explanation of stationary processes (and similar fundamental issues) is woefully inadequate. Also, entire chapters, such as spectral analysis chapter, are incredibly shallow and do not provide sufficient information for analyses - the introduction for that chapter is only 2 pages and leaves out substantive background material.
2. The equations throughout the book need more development and explanation and should be more closely tied to the R code. One route towards this goal would be to show more "under the hood" programming, rather than blanket functions or packages that do not provide insight into how analyses are completed.
3. The overall organization needs more thought, for example, cross-referencing between chapters, providing an overview of concepts in a broad introductory chapter, and including a synthesis to put everything all together.
4. The graduate group interested in this topic was frustrated by a lack of clarity - even a tool as simple as a glossary could have cut down on the excessive amount of consulting other resources, or internet searches of terms and concepts for more detail.
5. The analyses of simulated or actual data were a particular strength of the book, but these were used less frequently as the book progressed, and throughout the book, there was very little discussion of what the results mean.
6. It is unfortunate, given the state of big data, that researchers (such as ecologists) who require rigorous time series analyses have hesitated to utilize these approaches; this book could have been part of a turning point for more scientists to enter a time series boon, but it is not.
It is very much a multi-lesson tutorial on the basics of time series analysis, and should be worked through at the computer using R. The topics include decomposition (e.g., extracting seasonality vs. trends), handling autocorrelation, forecasting (e.g., the Bass model in marketing forecasts), regression models, and some more advanced topics such as spectral analysis. In some of the later topics, math is unavoidable and is presented when needed.
There are two limitations to the book. First, as should be obvious from the preceding, some mathematicians and statisticians may be disappointed by the focus on tutorial rather than formal explanation. It has math but that's not the focus, so it would not be suitable for, say, a graduate-level mathematical stats course. Second, it of course cannot cover all aspects of time series analysis. It has examples from many domains (finance, operations, marketing, etc.) but limited depth in any single area; and it presents a variety of core models but does not cover the many advanced topics.
Overall this is an excellent introduction to time series. If you're a general R analyst who wants to get started with time series, it's the best place to begin that I've seen.
Only one knock, have been through several of the examples and there are some coding typos; nothing major but stay on your toes. Also, some of the algorithms may have changed since the book was written so you need to make use of the R help files to clear up any discrepancies with the author's work...some probably won't get cleared up because a more complex algorithm has been changed.
This is a book I've been looking for.