Introduction to time series and forecasting. 2nd ed.

*(English)*Zbl 0994.62085
Springer Texts in Statistics. New York, NY: Springer. xiv, 434 p. (2002).

The book gives an introduction into time series analysis. The emphasis is on methods and the analysis of data sets. For reading the book only basic knowledge in calculus, matrix algebra and elementary statistics is required. A CD-ROM is included with a student version of the time series package ITSM 2000. The package requires an IBM-compatible PC operating under Windows 95, NT version 4.0, or a later version of either of these systems. The data sets used in this book are available on the CD-ROM.

The book contains ten chapters. They are denoted as: Introduction, stationary processes, ARMA models, spectral analysis, modeling and forecasting with ARMA processes, nonstationary and seasonal time series models, multivariate time series, state-space models, forecasting techniques, and further topics. At the end of the book some basic results in probability theory and statistics are summarized and a tutorial of the software ITSM is given.

For the review of first edition of this book from 1996 see Zbl 0868.62067. In the present second edition several changes were made. Since the upgrade to ITSM 2000 occurred after the first edition, it was necessary to coordinate the new software with the text. Furthermore, some topics are treated in more detail in this new edition, like, e.g., the role of the innovations algorithm in generalized least squares and maximum likelihood estimation of regression models with time series errors, forecasting of ARIMA models, GARCH modeling, etc.

The book is highly recommendable. It provides an excellent introduction into time series analysis. Because the key mathematical results are stated without proof and no deeper mathematical knowledge is needed, it can be used as a textbook for students of various disciplines. Moreover, it is suitable as a reference book for practitioners. The great number of examples coming from economics, engineering, natural and social sciences contribute to a better understanding of the methods. For handling the software, very little familiarity with computing is required.

The book contains ten chapters. They are denoted as: Introduction, stationary processes, ARMA models, spectral analysis, modeling and forecasting with ARMA processes, nonstationary and seasonal time series models, multivariate time series, state-space models, forecasting techniques, and further topics. At the end of the book some basic results in probability theory and statistics are summarized and a tutorial of the software ITSM is given.

For the review of first edition of this book from 1996 see Zbl 0868.62067. In the present second edition several changes were made. Since the upgrade to ITSM 2000 occurred after the first edition, it was necessary to coordinate the new software with the text. Furthermore, some topics are treated in more detail in this new edition, like, e.g., the role of the innovations algorithm in generalized least squares and maximum likelihood estimation of regression models with time series errors, forecasting of ARIMA models, GARCH modeling, etc.

The book is highly recommendable. It provides an excellent introduction into time series analysis. Because the key mathematical results are stated without proof and no deeper mathematical knowledge is needed, it can be used as a textbook for students of various disciplines. Moreover, it is suitable as a reference book for practitioners. The great number of examples coming from economics, engineering, natural and social sciences contribute to a better understanding of the methods. For handling the software, very little familiarity with computing is required.

Reviewer: Wolfgang Schmid (Frankfurt an der Oder)

##### MSC:

62M10 | Time series, auto-correlation, regression, etc. in statistics (GARCH) |

62-01 | Introductory exposition (textbooks, tutorial papers, etc.) pertaining to statistics |

62-04 | Software, source code, etc. for problems pertaining to statistics |

62M15 | Inference from stochastic processes and spectral analysis |

62M20 | Inference from stochastic processes and prediction |