Time-Series Analysis

Preface; Part I. Overview: 1. The search for hidden structures; 2. The ubiquitous cycles; 3. How Slutzky created order from chaos; 4 Forecasting: Yule's autoregressive models; 5. Into the black box with white light; 6. Experimentation and change; Part II. Time-series models: 7. Models and the problem of correlated data; 8. An introduction to time-series models: stationarity; 9. What if the data are not stationary?; Part III. Deterministic and nondeterministic components: 10. Moving-average models; 11. Autoregressive models; 12. The complex behaviour of the second-order autoregressive process; 13. The partial autocorrelation function: completing the duality; 14. The duality of MA and AR processes; Part IV. Stationary frequency-domain models: 15. The spectral density function; 16. The periodogram; 17. Spectral windows and window carpentry; 18. Explanation of the Slutzky effect; Part V. Estimation in the time domain: 19. AR model fitting and estimation; 20. Box-Jenkins model fitting: the ARIMA models; 21. Forecasting; 22. Model fitting: worked example; Part VI. Bivariate time-series analysis: 23. Bivariate frequency-domain analysis; 24. Bivariate frequency example: mother-infant play; 25. Bivariate time-domain analysis; Part VII. Other Techniques: 26. The interrupted time-series experiment; 27. Multivariate approaches; Notes; References; Index.