Applied Time Series Analysis

Terence Mills is Professor of Applied Statistics and Econometrics at Loughborough University and has well over 200 publications, beginning in 1977 with a paper in the European Economic Review. He has since published in most of the international economic, economic history, econometrics, finance and statistics journals and in a range of other journals, including Journal of Climate, Climatic Change, Journal of Cosmology, International Journal of Body Composition Research, Physica A, Energy and Buildings, and Journal of Public Health. He has also written or edited almost 20 books, including a range of introductory statistics and econometric texts, handbooks on econometrics, and histories of time series analysis.

"In in his usual clear and masterful way, Terence Mills gives the reader a clear understanding of the central topics of modern time series analysis. This book is a ‘must read’ for students across a range of disciplines whose interest is in data that are generated sequentially in time. The book provides many practical computer-based examples that bring alive the key concepts in time series analysis. It will become a standard reference in its area." --Kerry Patterson, University of Reading"Applied Time Series Analysis should prove to be very useful for practical application as it blends together the modeling and forecasting of time series data employing insightful empirical examples. This book will be useful to both practitioners as well for those with extensive experience. The exposition of material is very clear and rigorous." --Mark Wohar, University of Nebraska

• 1. Time Series and Their Features2. Transforming Time Series3. ARMA Models for Stationary Time Series4. ARIMA Models for Nonstationary Time Series5. Unit Roots, Difference and Trend Stationarity, and Fractional Differencing6. Breaking and Nonlinear Trends7. An Introduction to Forecasting With Univariate Models8. Unobserved Component Models, Signal Extraction, and Filters9. Seasonality and Exponential Smoothing10. Volatility and Generalized Autoregressive Conditional Heteroskedastic Processes11. Nonlinear Stochastic Processes12. Transfer Functions and Autoregressive Distributed Lag Modeling13. Vector Autoregressions and Granger Causality14. Error Correction, Spurious Regressions, and Cointegration15. Vector Autoregressions With Integrated Variables, Vector Error Correction Models, and Common Trends16. Compositional and Count Time Series17. State Space Models18. Some Concluding Remarks