×

State space modeling of multiple time series. (English) Zbl 0733.62098

Summary: Time series methods offer the possibility of making accurate forecasts, even when the underlying structural model is unknown, by replacing the structural restrictions needed to reduce sampling error and improve forecasts with restrictions determined from the data. While there has been considerable success with relative simple univariate time series modeling procedures, the complex interrelationships possible with multiple series require more powerful techniques.
Based on the insights of linear systems theory, a multivariate state space method for both stationary and nonstationary problems is described and related to ARMA models. The states or dynamic factors of the procedure are chosen to be robust in the presence of model misspecification, in contrast to ARMA models which lack this property. In addition, by treating the model choice as a formal approximation problem certain new optimal properties of the procedure with respect to specification are established; in particular, it is shown that no other model of equal or smaller order fits the observed autocovariance sequence any better in the sense of a Hankel norm.
Finally, in the treatment of nonstationary series, a natural decomposition into long run and short run dynamics results in easily implemented two step procedures that use characteristics of the data to identify and model trend and cycle components that correspond to cointegration and error correction models. Applications include annual U.S. GNP and money stock growth rates, monthly California beef prices and inventories, and monthly stock prices for large retailers.

MSC:

62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
62P20 Applications of statistics to economics
91B84 Economic time series analysis
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Akaike H., System Identification (1976)
[2] Aoki M., Transactions on Automatic control 13 pp 246– (1976) · doi:10.1109/TAC.1968.1098900
[3] Aoki M., Optimal Control and System Theory in Dynamic Economic Analysis (1976) · Zbl 0349.90030
[4] Aoki M., State Space Modeling of Time Series (1987) · Zbl 0606.62102 · doi:10.1007/978-3-642-96985-0
[5] Aoki M., Oxford Bulletin of Economics and Statistics 50 pp 89– (1988)
[6] Aoki, M. Tests of Significance and Error Estimates of the Parameters of a Balanced States Space Model of Time Series. Conference on Time Series. June1989. Osaka, Japan: University of Osaka.
[7] Aoki, M. 1989. Singular Values, Canonical Correlation Coefficients, and the Dimension of State Space Model of Time Series. NSF/NBER Time Series Conference. September1989, Madrid, Spain.
[8] DOI: 10.1016/0304-4076(89)90002-X · Zbl 0692.62072 · doi:10.1016/0304-4076(89)90002-X
[9] DOI: 10.1109/TAC.1967.1098647 · doi:10.1109/TAC.1967.1098647
[10] Jenkins G. M., Time Series Analysis: Forecasting and Control. (1971)
[11] Byrnes C. I., Mimeo (1971)
[12] DOI: 10.1016/0165-1889(88)90044-9 · doi:10.1016/0165-1889(88)90044-9
[13] Chow G. C., Analysis and Control of Dynamic Economic Systems · Zbl 0314.90001
[14] DOI: 10.2307/1241600 · doi:10.2307/1241600
[15] Dorfman J. H., A Bayesian Approach to State Space Multivariate Time Series Modeling (1989)
[16] DOI: 10.2307/1913236 · Zbl 0613.62140 · doi:10.2307/1913236
[17] Faurre P. L., Operators Rationels Positifs. (1976)
[18] Gantmacher R. R., The Thoery of Matrices 2 (1960)
[19] Gilbert E. G., SIAM Journal of Control 1 2 pp 128– (1963)
[20] DOI: 10.2307/1391215 · doi:10.2307/1391215
[21] Golub G. H., Matrix Computations (1983) · Zbl 0559.65011
[22] Granger, C. W. J. 1983. ”Co-Integreated Variable and Error-Correcting Models”. San Diego: University of California. Economics Department Working Paper 83-13
[23] Hannan E. J., The Statistical Theory of Linear Systems (1988) · Zbl 0641.93002
[24] Havenner, A. and Aoki, M. 1988a. ”Econometrics and Linear System Theory in Multivariate Time Series Analysis”. Davis: University of California. · Zbl 0646.62106
[25] Havenner, A. and Aoki, M. 1988b. Proceeding of the 1988 American Statistical Association Business and Economic Statistics Section. State Space Modeling of Stationary Time Series: Theory and Applicatios. 1988b.
[26] Havenner, A. and Aoki, M. 1988c. ”Deterministic and Stochastic Trends in State Space Models of Nonstationary Time Series”. Davis: University of California. Agricultural Economics Working Paper
[27] Havenner A., Computers and Mathematics with Applacitions 17 pp 1177– (1988)
[28] DOI: 10.1086/296144 · doi:10.1086/296144
[29] HouseholderS A. S., The Theory of Matrices in Numerical Analysis (1964)
[30] Kailath T., Linear Systems (1980)
[31] DOI: 10.1109/TAC.1981.1102736 · Zbl 0553.93038 · doi:10.1109/TAC.1981.1102736
[32] Luenberger L. D., Introduction to Dynamic Systems: Theory, Models, and Applications (1979) · Zbl 0458.93001
[33] Mittnik S., System Theoretic Methods in Economic Modelling (1989) · Zbl 0679.00023
[34] DOI: 10.1016/0304-4076(80)90056-1 · Zbl 0425.62074 · doi:10.1016/0304-4076(80)90056-1
[35] Tsay R., Journal of Business and Economic Statistics 7 pp 327– (1987)
[36] Zellner A., Journal of Econometrics 2 pp 17– (1974) · Zbl 0282.90011 · doi:10.1016/0304-4076(74)90028-1
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.