Summary
In this paper it is shown that the famous Levinson-Durbin algorithm is just a recursive algorithm presented previously by Szegö.
Similar content being viewed by others
References
Anderson, T. W. (1971), The Statistical Analysis of Time Series, Wiley, New York.
Choi, B.S. (1992), ARMA Model Identification, Springer-Verlag, New York.
Choi, B.S. (1997), ‘A recursive algorithm for solving the spatial Yule-Walker equations of causal spatial AR models’, Statistics and Probability Letters 33, 241–251.
Durbin, J. (1960), ‘The fitting of time series models’, Inter. Statistical Review 28, 233–244.
Grenander, U. and Szegö, G. (1955), Toeplitz Forms and Their Applications, Chelsea Pub. Co., New York.
Haykin, S. (1996), Adaptive Filter Theory, 3rd edn., Prentice-Hall, New Jersey.
Justice, J.H. (1977), ‘A Levinson-type algorithm for two-dimensional Wiener filtering using bivariate Szegö polynomials’, Proc. IEEE 65, 882–886.
Levinson, N. (1947),‘The Wiener RMS (Root Mean Square) error criterion in filter design and prediction’, J. Mathematics and Physics 25, 261–278.
Szegö, G. (1921), ‘Beiträge zur Theorie der Toeplitzschen Formen II’, Mathematische Zeitschrift 9, 167–190.
Szegö, G. (1939), Orthogonal Polynomials, American Mathematical Society, New York.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Yi, S., Choi, B. Levinson-Durbin algorithm as a Szegö polynomial recursion. Computational Statistics 17, 59–64 (2002). https://doi.org/10.1007/s001800200090
Published:
Issue Date:
DOI: https://doi.org/10.1007/s001800200090