A course in time series analysis. Lectures of the ECAS '97, Madrid, Spain, September 15--19, 1997 (Q2707029)

[The articles of this volume will not be indexed individually.] NEWLINENEWLINENEWLINEThe book is based on the lectures of the ECAS'97 Course on time series analysis held in Spain. It includes contributions from eleven of the world's leading personalities in time series. The book brings together material previously available only in the professional literature and presents a unified view of the advanced procedures of time series building. It can be used as a principal or complementary text of time series courses for researchers, academic teachers of statistics and statistical professionals in practice. It presents suitable balance between theory and applications with many real data examples. NEWLINENEWLINENEWLINEThe book has three main parts, called (I) Basic concepts in univariate time series; (II) Advanced topics in univariate time series; (III) Multivariate time series; with the following chapters:NEWLINENEWLINENEWLINEPart I: 2. Univariate time series: autocorrelation, linear prediction, spectrum, and state-space model; 3. Univariate ARMA models; 4. Model fitting and checking, and the Kalman filter; 5. Prediction and model selection; 6. Qutliers, influential observations, and missing data; 7. Automatic modeling methods for univariate series; 8. Seasonal adjustment and signal extraction time series.NEWLINENEWLINENEWLINEPart II: 9. Heteroscedastic models; 10. Nonlinear time series models: testing and applications; 11. Bayesian time series analysis; 12. Nonparametric time series analysis: nonparametric regression, locally weighted regression, autoregression, and quantile regression; 13. Neural network models.NEWLINENEWLINENEWLINEPart III: 14. Vector ARMA models; 15. Cointegration in the VAR model; 16. Identification of linear dynamic multiinput/multioutput systems.