Abstract
This paper solves an open theoretical question in the identification stage of Scalar Component Models, posed initially by Tiao and Tsay and noted by several researchers, specifically as it refers to the choice of a certain parameter present in the process and which they denote h. The theoretical concept of sure overall orders, instead of the so-called overall orders, is useful in addressing this issue. Using simple examples, we justify the need for our theoretical results. Moreover, we use a Ranks Table and its properties to complement the SCM identification stage with interesting theoretical information without adding significant calculations to the procedure initially proposed by Tiao and Tsay.
Similar content being viewed by others
References
Athanasopoulos, G., Poskitt, D.S., Vahid, F.: Two Canonical VARMA Forms: Scalar Component Models Vis-à-Vis the Echelon Form. Monash Econometrics and Business Statistics Working Papers from Monash University, Department of Econometrics and Business Statistics, No. 10/07 (2009)
Athanasopoulos, G., Vahid, F.: A complete VARMA modelling methodology based on scalar components. J. Time Ser. Anal. 29(3), 533–554 (2008)
Bultheel, A., van Barel, M.: Linear Algebra, Rational Approximation and Orthogonal Polynomials. Studies in Computational Mathematics, North Holland (1997)
Lütkepohl, H., Poskitt, D.S.: Specification of Echelon-Form VARMA models. J. Bus. Econ. Stat. 14(1), 69–79 (1996)
Pestano-Gabino, C., González-Concepción, C.: Rationality, minimality and uniqueness of representation of matrix formal power series. J. Comput. Appl. Math. 94, 23–38 (1998)
Pestano-Gabino, C., González-Concepción, C., Gil-Fariña, M.C.: Sure overall orders to identify scalar component models. WSEAS Trans. Math. 5(1), 97–102 (2006)
Reinsel, G.C.: Elements of Multivariate Time Series Analysis. Springer, New York (1997)
Tiao, G.C., Tsay, R.S.: Model specification in multivariate time series. J. R. Stat. Soc. B 51(2), 157–213 (1989)
Tsay, R.S.: Two canonical forms for Vector ARMA processes. Stat. Sin. 1, 247–269 (1991)
Author information
Authors and Affiliations
Corresponding author
Additional information
This is an improved version of An Algebraic Analysis using Matrix Padé Approximation to Improve the Choice of Certain Parameter in Scalar Component Models Working Paper 10-08, Statistics and Econometrics Series 03, 2010, Department of Statistics, University Carlos III of Madrid (Spain). Work partially funded by Ministerio de Educación y Ciencia (MTM2008-06671 and MTM2006-14961-C05-03).
Rights and permissions
About this article
Cite this article
Pestano-Gabino, C., González-Concepción, C. & Gil-Fariña, M.C. A note on the initial identification of scalar component models. Numer Algor 58, 439–449 (2011). https://doi.org/10.1007/s11075-011-9462-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11075-011-9462-9