Abstract
This paper develops a method of adaptive modeling that may be applied to forecast non-stationary time series. The starting point are time-varying coefficients models introduced in statistics, econometrics and engineering. The basic step of modeling is represented by the implementation of adaptive recursive estimators for tracking parameters. This is achieved by unifying basic algorithms—such as recursive least squares (RLS) and extended Kalman filter (EKF)—into a general scheme and next by selecting its coefficients with the minimization of the sum of squared prediction errors. This defines a non-linear estimation problem that may be analyzed in the context of the conditional least squares (CLS) theory. A numerical application on the IBM stock price series of Box-Jenkins illustrates the method and shows its good forecasting ability.
Similar content being viewed by others
References
Box, G. E. P. and Jenkins, G. M. (1976). Time Series Analysis: Forecasting and Control, Holden-Day, San Francisco.
Chen, R. and Tsay, R. S. (1993). Functional coefficient autoregressive models, J. Amer. Statist. Assoc., 88, 298–311.
Goodwin, G. and Sin, K. S. (1984). Adaptive Filtering, Prediction and Control, Prentice-Hall, Englewood-Cliffs (NJ).
Grillenzoni, C. (1990). Modeling time-varying dynamical systems, J. Amer. Statist. Assoc., 85, 499–507.
Grillenzoni, C. (1993). ARIMA processes with ARIMA parameters, J. Bus. Econom. Statist., 11, 272–289.
Grillenzoni, C. (1994). Optimal recursive estimation of dynamic models, J. Amer. Statist. Assoc., 89, 777–787.
Guo, L. and Ljung, L. (1995a). Exponential stability of general tracking algorithms, IEEE Trans. Automat. Control, AC-40, 1376–1387.
Guo, L. and Ljung, L. (1995b). Performance analysis of general tracking algorithms, IEEE Trans. Automat. Control, AC-40, 1388–1402.
Kitagawa, G. (1987). Non-gaussian state-space modeling of Nonstationary time series, J. Amer. Statist. Assoc., 82, 1032–1041.
Kitagawa, G. and Gersh, W. (1985). A smoothness priors time-varying AR coefficient modeling of nonstationary time series, IEEE Trans. Automat. Control, AC-30, 48–56.
Klimko, L. A. and Nelson, P. I. (1978). On conditional least squares estimation for stochastic processes, Ann. Statist., 6, 629–642.
Kushner, H. (1990). Weak Convergence Methods and Singularly Perturbed Stochastic Control and Filtering Problems, Birkhauser, Berlin.
Ljung, L. and Söderström, T. (1983). Theory and Practice of Recursive Identification, The MIT Press, Cambridge (MA).
Meyn, S. and Tweedie, R. (1993). Markov Chains and Stochastic Stability, Springer, New York.
Pagan, A. (1980). Some identification and estimation results for regression models with stochastically varying coefficients, J. Econometrics, 13, 341–363.
Pourahmadi, M. (1986). On stationarity of the solution of a doubly stochastic model, J. Time Ser. Anal., 7, 123–131.
Rao, M. M. (1961). Consistency and limit distributions of estimators of parameters in explosive stochastic difference equations, Ann. Math. Statist., 32, 195–218.
Salgado, M. E., Goodwin, C. G. and Middleton, R. H. (1988). Modified least squares algorithms incorporating exponential resetting and forgetting, Internat. J. Control, 49, 477–491.
Tjostheim, D. (1986). Estimation of nonlinear time series models, Stochastic Process. Appl., 21, 225–273.
Tong, H. (1990). Nonlinear Time Series Analysis: A Dynamical System Approach, Claredon Press, Oxford (UK).
Weiss, A. A. (1984). Systematic sampling and temporal aggregation in time series models, J. Econometrics, 26, 271–281.
Widrow, B. and Stearns, S. D. (1985). Adaptive Signal Processing, Prentice-Hall, Englewood Cliffs (NJ).
Zellner, A., Hong, C. and Min, C. (1990). Forecasting turning points in international output growth rates, J. Econometrics, 49, 275–304.
Author information
Authors and Affiliations
About this article
Cite this article
Grillenzoni, C. Time-Varying Parameters Prediction. Annals of the Institute of Statistical Mathematics 52, 108–122 (2000). https://doi.org/10.1023/A:1004189000171
Issue Date:
DOI: https://doi.org/10.1023/A:1004189000171