Hiernaux, Alfredo G. and Casals Carro, José and Jerez Méndez, Miguel (2005) Fast estimation methods for time series models in statespace form. [ Documentos de Trabajo del Instituto Complutense de Análisis Económico (ICAE); nº 0504, 2005, ]

PDF
221kB 
Official URL: http://eprints.ucm.es/7881/
Abstract
We propose two fast, stable and consistent methods to estimate time series models expressed in their equivalent statespace form. They are useful both, to obtain adequate initial conditions for a maximumlikelihood iteration,
or to provide final estimates when maximumlikelihood is considered inadequate or costly. The statespace foundation of these procedures implies that they can estimate any linear fixedcoefficients model, such as ARIMA, VARMAX or structural time series models. The computational and finitesample performance of both methods is very good, as a simulation exercise shows.
Item Type:  Working Paper or Technical Report 

Uncontrolled Keywords:  Statespace models, Subspace methods, Kalman Filter, System identification 
Subjects:  Social sciences > Economics > Econometrics 
Series Name:  Documentos de Trabajo del Instituto Complutense de Análisis Económico (ICAE) 
Volume:  2005 
Number:  0504 
ID Code:  7881 
References: 
Anderson, B. D. O. and Moore, J. B. (1979). Optimal Filtering. Englewood Cliﬀs (N.J.): Prentice Hall. Ansley, C. F. and Newbold, P. (1980). Finite sample properties of estimators for autorregresion moving average models. Journal of Econometrics, 13:159–183. Aoki, M. (1990). State Space Modelling of Time Series. Springer Verlag, New York. Casals, J., Sotoca, S., and Jerez, M. (1999). A fast stable method to compute the likelihood of time invariant state space models. Economics Letters, 65(3):329–337. Chui, N. L. C. (1997). Subspace Methods and Informative Experiments for System Identiﬁcation. PhD thesis, Pembroke College Cambridge. Dufour, J. M. and Pelletier, D. (2004). Linear estimation of weak varma models with macroeconomic applications. Technical report, Centre Interuniversitaire de Recherche en Economie Quantitative (CIREQ), Universit´e de Montr´eal, CANADA. Favoreel, W., De Moor, B., and Van Overschee, P. (2000). Subspace state space system identiﬁcation for industrial processes. Journal of Process Control, 10:149–155. Flores, R. and Serrano, G. (2002). A generalized least squares estimation method for varma models. Statistics, 36(4):303–316. Francq, C. and Zako¨ıan, J. M. (2000). Estimating weak garch representations. Econometric Theory, 16:692–728. Harvey, A. C. (1989). Forecasting, structural time series models and th Kalman Filter. Cambridge University Press. Harvey, A. C., Ruiz, E., and Shepard, N. (1994). Multivariate stochastic variance models. Review of Economic Studies, 61:247–264. Harvey, A. C. and Shepard, N. (1993). Structural Time Series Models, volume 11 of Handbook of Statistics. Elsevier Science Publishers B.V. Ho, B. and Kalman, R. (1966). Eﬀective construction of linear statevariable models from inputoutput functions. Regelungstechnik, 14:545–548. Koreisha, S. G. and Pukkila, T. H. (1989). Fast linear estimation methods for vector autorregresive moving average models. Journal of Time Series Analysis, 10:325–339. Koreisha, S. G. and Pukkila, T. H. (1990). A generalized leastsquares approach for estimation of autorregresive movingaverage models. Journal of Time Series Analysis, 11:139–151. Ljung, L. (1999). System Identiﬁcation, Theory for the User. PTR Prentice Hall. Lütkepohl, H. and Poskitt, D. S. (1996). Speciﬁcation of echelon form varma models. Journal of Business and Economic Statistics, 14(1):69–79. Peternell, K., Sherrer, W., and Deistler, M. (1996). Statistical analysis of novel subspace identiﬁcation methods. Signal Processing, 52:161–177. Spliid, H. (1983). A fast estimation method for the vector autoregressive moving average model with exogenous variables. Journal of the American Statistical Association, 78(384):843–849. Terceiro, J. (1990). Estimation of Dynamics Econometric Models with Errors in Variables. SpringerVerlag, Berlin. Van Overschee, P. and De Moor, B. (1996). Subspace Identiﬁcation for Linear Systems: Theory, Implementation, Applications. Kluwer Academic, Dordrecht, The Netherlands. Viberg, M. (1995). Subspacebased methods for the identiﬁcation of the linear timeinvariant systems. Automatica, 31(12):1835–1852. 
Deposited On:  05 May 2008 
Last Modified:  06 Feb 2014 07:56 
Repository Staff Only: item control page