Providing a practical introduction to state space methods as applied to unobserved components time series models, also known as structural time series models, this book introduces time series analysis using state space methodology to readers who are neither familiar with time series analysis, nor with state space methods. The only background required in order to understand the material presented in the book is a basic knowledge of classical linear regression models, of which a brief review is provided to refresh the reader's knowledge. Also, a few sections assume familiarity with matrix algebra, however, these sections may be skipped without losing the flow of the exposition.
The book offers a step by step approach to the analysis of the salient features in time series such as the trend, seasonal, and irregular components. Practical problems such as forecasting and missing values are treated in some detail. This useful book will appeal to practitioners and researchers who use time series on a daily basis in areas such as the social sciences, quantitative history, biology and medicine. It also serves as an accompanying textbook for a basic time series course in econometrics and statistics, typically at an advanced undergraduate level or graduate level.
Interested readers can download all the Ox code and data sets in zip format for performing the analyses presented in the book simultaneously here.
Alternatively, the Ox code and corresponding data set(s) from each chapter can be downloaded separately here:
|Chapter 2||The Local Level Model|
|Chapter 3||The Local Linear Trend Model|
|Chapter 4||The Local Level Model with Seasonal|
|Chapter 5||The Local Level Model with Explanatory Variable|
|Chapter 6||The Local Level Model with Intervention Variable|
|Chapter 7||The UK Seat Belt and Inflation Models|
|Chapter 8||General Treatment of Univariate State Space Models|
|Chapter 9||Multivariate Time Series Analysis|
|Chapter 10||State Space and Box-Jenkins Methods for Time Series Analysis|
|Chapter 11||State Space Modelling in Practice|
Note that the code is written using SsfPack Extended. However, many of the provided examples can
also run on SsfPack Basic after replacing the functions ending on
Ex with the corresponding
functions from SsfPack Basic.
We discovered that two persons have taken the time and effort to develop and provide open source R code for the analysis of (some of) the examples in our book. One person is Radhakrishna, and his R code for the English speaking community can be seen here, the other is Ono Shigeru, and his code for the Japanese speaking community can be seen here.
Two quotes from the first review by T. Sabin on Amazon:
This is the book that I wish was available when I first began using state space time series models ...
Overall, if you would like to understand state space time series analysis and like learning by example then this is a good place to start.
Two quotes from the second and first five-star review by Roy Marsten on Amazon:
I found this book extremely helpful and I highly recommend it ...
I have read the classics: Harvey (1989) and Durbin and Koopman (2002) and they are great, but they leave out all the practical stuff. ... How do we actually use this stuff? That is where Commandeur & Koopman is invaluable.
A quote from the first official review of the book by dr. P.H.C. (Paul) Eilers as it appeared in the March 2008 Newsletter of the Dutch Classification Society:
I really recommend this book. It is a very good read and it is very reasonably priced.
Once you know SPMs, you don't need any other time series methods.
Four quotes from a second official review of the book by Mark Pickup as it appeared in the Spring 2009 Newsletter (Volume 16, Number 2) of the Political Methodology Section of the American Political Science Association:
Although maybe not immediately apparent, this book
has the potential to substantially contribute to political science.
Commandeurís decision to publish, with
Koopman, his personal notes on state space methods in a
manner that promises to help close the gaps in information
and knowledge within the social sciences is most welcome.
As an introduction to a complex subject, this book
(...) if one is interested in utilizing state space methods, this book
provides an excellent entry point. For those not so much
interested in using state space methods, as they are simply
curious exactly what they are all about, this book also
provides a surprisingly easy-to-read overview.
Another five-star review by Amazonian on Amazon:
This book should be renamed "The First Book You Should Read in State Space Time Series Analysis". A short book, it presents all the basic concepts in state space models very clearly. It's almost fun to read it. Not suitable if you already know the basics and want to get more hands-on experience with SS models.
Yet another five-star review by "Financial Economics" on Amazon:
"When it comes to State Space methods, Koopman is the author that needs to be on your radar screen."
"This is the #1 text needed to commence your initial investigations."
"After reading this text, you should be better prepared for the Durbin and Koopman text."
"You should force yourself to learn to program Kalman Filter - find existing code and translate it."
"I highly recommend Oxmetrics software with STAMP and SSFPACK to implement models."
"A third text to explore is State Space and Unobserved Component Models: Theory and Applications by Harvey, Koopman and Shepard. By then you have a strong foundation."
Two quotes from a fourth five-star review by John Smallberries on Amazon:
"This slim book clearly lays out the connections between classic linear regression and state space models for time series data."
"As others say, this is definitely an introduction, not a reference - you likely will not return to it once consumed. But what a fine meal!"
A list of corrections and additions to the book can be downloaded here in pdf format.
An Introduction to State Space Time Series Analysis by Jacques J.F. Commandeur and Siem Jan Koopman was published on July 19, 2007, as Volume 1 in the Practical Econometrics series by Oxford University Press, and can be ordered from OUP-UK, OUP-US, and Amazon, amongst others.
The book has been translated in Japanese in 2009 by Hajime Wago, and this translated version can be ordered from Amazon Japan.
The book has also been translated in Chinese by Huan Zhijian and published by China Financial Publishing House in July 2015. This translation of the book can be obtained from Amazon China.