Chatfield, C: Analysis of Time Series

INTRODUCTION Some Representative Time Series Terminology Objectives of Time-Series Analysis Approaches to Time-Series Analysis Review of Books of Time Series SIMPLE DESCRIPTIVE TECHNIQUES Types of Variation Stationary Time Series The Time Plot Transformation Analysing Series that Contain a Trend Analysing Series that Contain Seasonal Variation Autocorrelation and the Correlogram Other Tests of Randomness Handling Real Data PROBABILITY MODELS FOR TIME SERIES Stochastic Processes and their Properties Stationary Processes Some Properties of the Autocorrelation Function Some Useful Models The Wold Decomposition Theorem FITTING TIME-SERIES MODELS (IN THE TIME DOMAIN) Estimating the Autocovariance and Autocorrelation Functions Fitting an Autoregressive Process Fitting a Moving Average Process Estimating the Parameters of an ARMA Model Estimating the Parameters of an ARIMA Model The Box-Jenkins Seasonal (SARIMA) Model Residual Analysis General Remarks on Model Building FORECASTING Introduction Univariate Procedures Multivariate Procedures A Comparative Review of Forecasting Procedures Some Examples Prediction Theory STATIONARY PROCESSES IN THE FREQUENCY DOMAIN Introduction The Spectral Distribution Function The Spectral Density Function The Spectrum of a Continuous Process Derivation of Selected Spectra SPECTRAL ANALYSIS Fourier Analysis A Simple Sinusoidal Model Periodogram Analysis Spectral Analysis: some Consistent Estimation Procedures Confidence Intervals for the Spectrum A Comparison of Different Estimation Procedures Analysing a Continuous Time Series Examples and Discussion BIVARIATE PROCESSES The Cross-Covariance and Cross-Correlation Functions The Cross-Spectrum LINEAR SYSTEMS Introduction Linear systems in the Time Domain Linear Systems in the Frequency Domain Identification of Linear Systems STATE-SPACE MODELS AND THE KALMAN FILTER State-Space Models The Kalman Filter NON-LINEAR MODELS Introduction Some Models with Nonlinear Structure Models for Changing

"quite possibly the most accessible introductory text on the subject. Chatfield's is most highly recommended whether as a teaching text or one for self-instruction." - Journal of the Royal Statistical Society, Issue 167 (4) "This textbook is well-known for everyone who is interested in time series analysisa substantial revision has taken placeit is an excellent textbook for undergraduate and postgraduate students, and can also be used by research workers as a reference or for self-tuition." -Zentralblatt MATH 1050 ..." there is no question that this text is the most accessible text on time series in existence..." -Dennis Cox, Rice University "The author's conversational style helps the reader to understand inherently difficult topics." - Journal of Quality Technology "This well-written book provides an excellent nontechnical introduction..." - Journal of the American Statistical Association ..."the only book I would recommend to readers for a safe, practically minded, non-mathematical introduction to a fairly broad cross section of topics..." - Neville Davies, Nottingham Trent University