'This textbook strikes an excellent balance between explaining the underlying concepts and intuition, containing the requisite amount of rigor, and providing sufficient guidance for students to be able to apply the methods described to a variety of time-series situations. It is extremely clearly written and should instantly find a wide audience. The book's emphasis on maximum-likelihood as a unifying guiding principle is well-justified, and provides the right context for students to understand how seemingly disparate econometric methods are fundamentally related.' Yacine Ait-Sahalia, Princeton University
Part I. Maximum Likelihood: 1. The maximum likelihood principle; 2. Properties of maximum likelihood estimators; 3. Numerical estimation methods; 4. Hypothesis testing; Part II. Regression Models: 5. Linear regression models; 6. Nonlinear regression models; 7. Autocorrelated regression models; 8. Heteroskedastic regression models; Part III. Other Estimation Methods: 9. Quasi-maximum likelihood estimation; 10. Generalized method of moments; 11. Nonparametric estimation; 12. Estimation by stimulation; Part IV. Stationary Time Series: 13. Linear time series models; 14. Structural vector autoregressions; 15. Latent factor models; Part V. Non-Stationary Time Series: 16. Nonstationary distribution theory; 17. Unit root testing; 18. Cointegration; Part VI. Nonlinear Time Series: 19. Nonlinearities in mean; 20. Nonlinearities in variance; 21. Discrete time series models; Appendix A. Change in variable in probability density functions; Appendix B. The lag operator; Appendix C. FIML estimation of a structural model; Appendix D. Additional nonparametric results.