Hostname: page-component-78c5997874-g7gxr Total loading time: 0 Render date: 2024-11-05T05:04:59.215Z Has data issue: false hasContentIssue false
  • English
  • Français

Multivariate linear time series models

Published online by Cambridge University Press:  01 July 2016

E. J. Hannan  and
L. Kavalieris
E. J. Hannan*
Affiliation:
The Australian National University
L. Kavalieris*
Affiliation:
The Australian National University
*
∗Postal address: Department of Statistics, IAS, Mathematical Sciences Building, The Australian National University, G.P.O. Box 4, Canberra ACT 2601, Australia.
∗Postal address: Department of Statistics, IAS, Mathematical Sciences Building, The Australian National University, G.P.O. Box 4, Canberra ACT 2601, Australia.
Get access Rights & Permissions [Opens in a new window]

Abstract

This paper is in three parts. The first deals with the algebraic and topological structure of spaces of rational transfer function linear systems—ARMAX systems, as they have been called. This structure theory is dominated by the concept of a space of systems of order, or McMillan degree, n, because of the fact that this space, M(n), can be realised as a kind of high-dimensional algebraic surface of dimension n(2s + m) where s and m are the numbers of outputs and inputs. In principle, therefore, the fitting of a rational transfer model to data can be considered as the problem of determining n and then the appropriate element of M(n). However, the fact that M(n) appears to need a large number of coordinate neighbourhoods to cover it complicates the task. The problems associated with this program, as well as theory necessary for the analysis of algorithms to carry out aspects of the program, are also discussed in this first part of the paper, Sections 1 and 2.

The second part, Sections 3 and 4, deals with algorithms to carry out the fitting of a model and exhibits these algorithms through simulations and the analysis of real data.

The third part of the paper discusses the asymptotic properties of the algorithm. These properties depend on uniform rates of convergence being established for covariances up to some lag increasing indefinitely with the length of record, T. The necessary limit theorems and the analysis of the algorithms are given in Section 5. Many of these results are of interest independent of the algorithms being studied.

Keywords

ARMAX MODELSLINEAR SYSTEMSHANKEL MATRIXANALYTIC MANIFOLDCOORDINATESECHELON FORMSTATE-SPACE FORMALGORITHMAUTOREGRESSIONLEVIN SON–WHITTLE RECURSIONAICBICORDER DETERMINATIONSIMULATIONMARTINGALE DIFFERENCESLAW OF ITERATED LOGARITHMCENTRAL LIMIT THEOREM
Type
Research Article
Information
Advances in Applied Probability , Volume 16 , Issue 3 , September 1984 , pp. 492 - 561
Copyright
Copyright © Applied Probability Trust 1984 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

[1] Akaike, H. (1969) Fitting autoregressive models for prediction. Ann. Inst. Statist. Math. 21, 243–247.CrossRefGoogle Scholar
[2] Akaike, H. (1974) Markovian representations of stochastic processes and its application to the analysis of autoregressive moving average processes. Ann. Inst. Statist. Math. 26, 363–387.Google Scholar
[3] Akaike, H. (1976) Canonical correlation analysis of time series and the use of an information criterion. In System Identification: Advances and Case Studies, ed. Mehra, R. K. and Lainiotis, D. G., Academic Press, New York, 27–96.Google Scholar
[4] An, Hong-Zhi; Chen, Zhao-Guo and Hannan, E. J. (1982) Autocorrelation, autoregression and autoregressive approximation. Ann. Statist. 10, 926–936.CrossRefGoogle Scholar
[5] Anderson, B. D. O. and Moore, J. B. (1979) Optimal Filtering. Prentice-Hall, New York.Google Scholar
[6] Antoulas, A. C. (1981) On canonical forms for linear constant systems. Internat. J. Control 33, 95–122.Google Scholar
[7] Astrom, K. J. and Mayne, D. Q. (1982) A new algorithm for recursive estimation of parameters in controlled ARMA processes. Proc. 6th IFAC Symp. Identification and System-Parameter Estimation, Arlington, VA, 122–126.Google Scholar
[8] Bard, Y. (1974) Nonlinear Parameter Estimation. Academic Press, New York.Google Scholar
[9] Box, G. E. P. and Jenkins, G. M. (1970) Time Series Analysis, Forecasting and Control. Holden-Day, San Francisco.Google Scholar
[10] Brockett, R. W. (1970) Finite Dimensional Linear Systems. Wiley, New York.Google Scholar
[11] Clark, J. M. C. (1976) The consistent selection of parametrization in systems identification. Paper presented at JACC, Purdue University.Google Scholar
[12] Cooper, D. M. and Wood, E. F. (1982) Identifying multivariate time series models. J. Time Series Anal. 3, 153–164.CrossRefGoogle Scholar
[13] Deistler, M. (1983) The properties of the parametrization of ARMAX systems and their relevance for structural estimation and dynamic specification. Econometrica 51, 1187–1208.CrossRefGoogle Scholar
[14] Deistler, M. and Hannan, E. J. (1981) Some properties of the parametrization of ARMA systems with unknown order. J. Multivariate Anal. 11, 474–484.Google Scholar
[15] Durbin, J. (1960) The fitting of time series models. Rev. Internat. Inst. Statist. 28, 233–244.CrossRefGoogle Scholar
[16] Engle, R. and Watson, M. (1981) A one factor multivariate time series model of metropolitan wage rates. J. Amer. Statist. Assoc. 76, 774–781.Google Scholar
[17] Hannan, E. J. (1969) The identification of vector mixed autoregressive-moving average systems. Biometrika 57, 223–225.Google Scholar
[18] Hannan, E. J. (1970) Multiple Time Series. Wiley, New York.CrossRefGoogle Scholar
[19] Hannan, E. J. (1971) The identification problem for multiple equation systems with moving average errors. Econometrica 39, 751–766.Google Scholar
[20] Hannan, E. J. (1979) The statistical theory of linear systems. In Developments in Statistics, ed. Krishnaiah, P. R., Academic Press, New York, 83–171.Google Scholar
[21] Hannan, E. J. (1979) The central limit theorem for time series regression. Stoch. Proc. Appl. 9, 281–289.CrossRefGoogle Scholar
[22] Hannan, E. J. (1980) The estimation of the order of an ARMA process. Ann. Statist. 8, 1071–1081.CrossRefGoogle Scholar
[23] Hannan, E. J. (1981) Estimating the dimenson of a linear system. J. Multivariate Anal. 11, 458–473.CrossRefGoogle Scholar
[24] Hannan, E. J. and Kavalieris, L. (1983) The convergence of autocorrelations and autoregressions. Austral. J. Statist. 25, 287–297.Google Scholar
[25] Hannan, E. J. and Kavalieris, L. (1984) Regression, autoregression models. Submitted for publication.Google Scholar
[26] Hannan, E. J. and Rissanen, J. (1982) Recursive estimation of ARMA order. Biometrika 69, 81–94.Google Scholar
[27] Hannan, E. J., Dunsmuir, W. M. and Deistler, M. (1979) Estimation of vector ARMAX models. J. Multivariate Anal. 10, 275–295.Google Scholar
[28] Hartman, P. and Wintner, A. (1941) On the law of the iterated logarithm. Amer. J. Math. 63, 169–176.CrossRefGoogle Scholar
[29] Ibragimov, I. A. and Linnik, Yu. V. (1971) Independent and Stationary Sequences of Random Variables. Wolters-Noordhoff, Groningen.Google Scholar
[30] Jain, N. C., Jogdeo, K. and Stout, W. F. (1975) Upper and lower functions for martingales and mixing processes. Ann. Prob. 3, 119–145.Google Scholar
[31] Jones, J. W. (1914) Fur Farming in Canada. Commission of Conservation, Ottawa.Google Scholar
[32] Kalman, R. E. (1960) A new approach to linear filtering and prediction problems. J. Basic Engineering 82, 35–45.Google Scholar
[33] Kalman, R. E. (1965) The algebraic structure of linear dynamical systems. I. The module of X. Proc. Nat. Acad. Sci. USA 54, 1503–1508.CrossRefGoogle Scholar
[34] Kalman, R. E. (1974) Algebraic geometric description of the class of linear systems of constant dimension. 8th Annual Princeton Conf. Information Sciences and Systems. Google Scholar
[35] Kendall, M. G. and Stuart, A. (1966) The Advanced Theory of Statistics, Vol. 3. Hafner, New York.Google Scholar
[36] Konvalina, I. S. and Matusek, M. R. (1979) Simultaneous estimation of poles and zeros in speech analysis and ITIF-Iterative inverse filtering algorithm. IEEE ASSP 27, 485–492.Google Scholar
[37] Makhoul, J. (1981) Lattice methods in spectral estimation. In Applied Time Series Analysis II, ed. Findley, D. F., Academic Press, New York, 301–326.Google Scholar
[38] Moricz, F. (1976) Moment inequalities and the strong law of large numbers. Z. Wahrscheinlichkeitsth. 35, 298–314.CrossRefGoogle Scholar
[39] Nicholls, D. F. (1976) The efficient estimation of vector linear time series models. Biometrika 63, 381–390.CrossRefGoogle Scholar
[40] Nicholls, D. F. and Hall, A. D. (1979) The exact likelihood function of stationary autoregressive–moving average models. Biometrika 66, 259–264.Google Scholar
[41] Rissanen, J. (1978) Modelling by shortest data description. Automatica 14, 465–471.CrossRefGoogle Scholar
[42] Rissanen, J. (1983) Universal prior for parameters and estimation by minimum description length. Ann. Statist. 11, 416–431.CrossRefGoogle Scholar
[43] Rosenbrock, H. H. (1970) State Space and Multivariable Theory. Wiley, New York.Google Scholar
[44] Schwarz, G. (1978) Estimating the dimension of a model. Ann. Statist. 6, 461–464.Google Scholar
[45] Shibata, R. (1980) Asymptotically efficient selection of the order of the model for estimating parameters of a linear process. Ann. Statist. 8, 147–164.Google Scholar
[46] Shibata, R. (1981) An optimal autoregressive spectral estimate. Ann. Statist. 9, 300–306.Google Scholar
[47] Solo, V. (1984) The exact likelihood for a multivariate ARMA model. J. Multivariate Anal. 14.Google Scholar
[48] Stout, W. F. (1970) The Hartman-Winter law of the iterated logarithm for martingales. Ann. Math. Statist. 41, 2158–2160.Google Scholar
[49] Tiao, G. C. and Box, G. E. P. (1981) Modelling multiple time series with applications. J. Amer. Statist. Assoc. 70, 802–816.Google Scholar
[50] Van Overbeek, A. J. M. (1982) On the structure selection for the identification of multivariate systems. Department of Electrical Engineering, Linkopping.Google Scholar
[51] Wang, Shou-Ren and Chen, Zhao-Guo (1983) Estimation of the order of ARMA model by a linear procedure. Forthcoming.Google Scholar
[52] Wertz, V., Gevers, M. and Hannan, E. J. (1982) The determination of optimum structures for the state space representation of multivariate stochastic processes. IEEE Trans. Automatic Control AC-27, 1200–1211.Google Scholar
[53] Whittle, P. (1963) On the fitting of multivariate autoregression and the approximate canonical factorisation of a spectral density matrix. Biometrika 50, 129–134.Google Scholar