Time series analysis: forecasting and control
The book is concerned with the building of models for discrete time series and dynamic systems. It describes in detail how such models may be used to obtain optimal forecasts and optimal control action. All the techniques are illustrated with examples using economic and industrial data. In Part 1, models for stationary and nonstationary time series are introduced, and their use in forecasting is discussed and exemplified. Part II is devoted to model building, and procedures for model identification, estimation, and checking which are then applied to the forecasting of seasonal time series. Part III is concerned with the building of transfer function models relating the input and output of a dynamic system computed by noise. In Part IV it is shown how transfer function and time series models may be used to design optimal feedback and feedforward control schemes. Part V contains an outline of computer programs useful in making the needed calculations and also includes charts and tables of value in identifying the models. (Author).
Avis des internautes - Rédiger un commentaire
Aucun commentaire n'a été trouvé aux emplacements habituels.
INTRODUCTION AND SUMMARY
STOCHASTIC MODELS AND THEIR
LINEAR STATIONARY MODELS
28 autres sections non affichées
Autres éditions - Tout afficher
added noise approximate ARIMA auto autoregressive operator autoregressive process behavior calculated Chapter chart coefficients computed conditional expectations consider control action control equation control scheme convergence correlation function covariance cross correlation cross correlation function cross covariance d d d d d d deviation diagnostic checking difference equation differencing discrete distribution dynamic estimated autocorrelations example exponentially first-order fitted forecast errors given Hence identification illustrate impulse response initial estimates input invertibility iteration lead least squares estimates likelihood function linear matrix mean square error moving average process nonstationary observations obtained optimal output partial autocorrelation function particular periodogram process of order Program quadratic recursive residuals roots sampling interval second-order Section shows spectrum standard error starting values stationary process step response stochastic model stochastic process substituting sum of squares Suppose Table transfer function model unit circle variable variance viscosity weights white noise zero