Elements of multivariate time series analysis (Q5907048)

[For the review of the first edition from 1993 see Zbl 0783.62072.] The book is a revised edition with several new topics. The most important new addition concerns so-called ARMAX models including some consideration of multivariate linear regression models with ARMA noise structure for errors. The book consists of 8 chapters: 1. Vector time series and model representations. 2. Vector ARMA time series models and forecasting. 3. Canonical structure of vector ARMA models. 4. Initial model building and least squares estimation for vector AR models. 5. Maximum likelihood estimation and model checking for vector ARMA models. 6. Reduced-rank and nonstationary cointegrated models. 7. State-space models, Kalman filtering, and related topics. 8. Linear models with exogenous variables. Some of the presented topics are generalizations of similar problems for univariate series to the multivariate case. In addition to that the author pays attention to topics that are special for multivariate time series analysis, as canonical structure of vector ARMA models, cointegrated models, etc.