Geodesic
Parametric identification of quasilinear difference equation
Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika, Tome 11 (2019) no. 4, pp. 32-38 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

Identification of the quasilinear difference equation is reduced to the problem of regression analysis with mutually dependent observable variables. This makes the classical solution schemes, based on the least squares method and its variations, ineffective. Finding estimates of the autoregressive equation coefficients is significantly complicated by poor conditionality of the system of equations, which represent necessary conditions for the minimum sum of squared deviations. In this case, estimates of the problem parameters are untenable. For solving such problems, it is possible to use the generalized least absolute deviations (GLAD) method, reduced to problems sequence of estimates of the autoregressive equation coefficients with the weighted least absolute deviations (WLAD) method. The article proposes an algorithm for solving the problem of WLAD-estimation, based on its conversion to the problem of linear programming (LP) of simple structure. The simplicity of the admissible set of the LP problem structure lies in the intersection of a linear subspace with a parallelepiped. It allows to propose an effective algorithm for its solution based on the gradient projection method. The algebraic computational complexity of the proposed algorithm does not exceed the value $O(N^2M^2)$, where $N$ is the number of coefficients in the equation under study, and $M$ is the number of the observed values. This WLAD computational complexity estimate is considered the best among the known ones.
Keywords: least absolute deviations, autoregressive model, linear programming, gradient projection method, computational complexity. 
@article{VYURM_2019_11_4_a3,
     author = {A. V. Panyukov and Ya. A. Mezaal},
     title = {Parametric identification of quasilinear difference equation},
     journal = {Vestnik \^U\v{z}no-Uralʹskogo gosudarstvennogo universiteta. Seri\^a, Matematika, mehanika, fizika},
     pages = {32--38},
     year = {2019},
     volume = {11},
     number = {4},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VYURM_2019_11_4_a3/}
}
TY  - JOUR
AU  - A. V. Panyukov
AU  - Ya. A. Mezaal
TI  - Parametric identification of quasilinear difference equation
JO  - Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika
PY  - 2019
SP  - 32
EP  - 38
VL  - 11
IS  - 4
UR  - http://geodesic.mathdoc.fr/item/VYURM_2019_11_4_a3/
LA  - ru
ID  - VYURM_2019_11_4_a3
ER  - 
%0 Journal Article
%A A. V. Panyukov
%A Ya. A. Mezaal
%T Parametric identification of quasilinear difference equation
%J Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika
%D 2019
%P 32-38
%V 11
%N 4
%U http://geodesic.mathdoc.fr/item/VYURM_2019_11_4_a3/
%G ru
%F VYURM_2019_11_4_a3
A. V. Panyukov; Ya. A. Mezaal. Parametric identification of quasilinear difference equation. Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika, Tome 11 (2019) no. 4, pp. 32-38. http://geodesic.mathdoc.fr/item/VYURM_2019_11_4_a3/

[1] N. S. Raybman, What is Identification?, Nauka Publ., M., 1970, 119 pp. (in Russ.)

[2] G. Gabisch, H. W. Lorenz, Business Cycle Theory, Springer-Verlag, 1989, 250 pp. | DOI | Zbl

[3] S. Davies, “Inter-Firm Diffusion of Process Innovations”, European Economic Review, 12:4 (1979), 299–317 | DOI

[4] I. Grabec, W. Sachse, Synergetics of Measurements, Prediction and Control, Springer Series in Synergetics, 68, Springer Verlag, Berlin–New York, 1997, 458 pp. | DOI | MR

[5] A. V. Panyukov, Y. A. Mezaal, “Stable Identification of Linear Autoregressive Model with Exogenous Varia-Bles on the Basis of the Generalized least Absolute Deviation Method”, Bulletin of the South Ural State University. Series “Mathematical Modelling, Programming Computer Software”, 11:1 (2018), 35–43 | DOI | Zbl

[6] A. V. Panyukov, Y. A. Mezaal, “Stable estimation of autoregressive model parameters with exogenous variables on the basis of the generalized least absolute deviation method”, IFAC-PapersOnLine, 51:11 (2018), 1666–1669 | DOI

[7] A. V. Panyukov, I. A. Tetin, Y. A. Mezaal, “Linkage Between Wlad and Glad and its Applications for Autoregressive Analysis”, Proceedings of the 4th International Conference ‘`Information Technologies for Intelligent Decision Making Support (ITIDS’2016)", 2016, 224–227

[8] M. Minoux, Programmation mathematique: theorie et algorithmes, Dunod, Paris, 1983 (in French) | MR | Zbl

[9] J. B. Rosen, “The Gradient Projection Method for Nonlinear Programming. Part 1: Linear Constraints”, Journal S.I.A.M., 8 (1960), 181–217 | MR | Zbl

[10] L. S. Gurin, “On the Consistency of the Least Squares Method Estimates”, Mathematical Support of Space Experiments, Collection of Scientific Papers, Nauka, M., 1978, 69–81 (in Russ.)

[11] V. I. Mudrov, V. L. Kushko, Methods for Processing Measurements: Quasilike Estimates, URSS Publ., M., 2014, 302 pp. (in Russ.)

[12] A. L. Shestakov, A. V. Keller, G. A. Sviridyuk, “The Theory of Optimal Measurements”, Journal of Computational and Engineering Mathematics, 1:1 (2014), 3–16 (in Russ.) | Zbl

[13] P. Huber, E. M. Ronchetti, Robust Statistics, Wiley, New York, 2009, 354 pp. | DOI | MR | Zbl

[14] P. Bloomheld, W. Steiger, Least Absolute Deviations Theory, Applications, and Algorithms, Birkhauser, Boston–Basel–Stuttgart, 1983, 351 pp. | DOI | MR

[15] J. Pan, H. Wang, Y. Qiwei, “Weighted Least Absolute Deviations Estimation for ARMA Models with Infinite Variance”, Econometric Theory, 23:3 (2007), 852–879 | DOI | MR | Zbl

[16] A. Panyukov, A. Tyrsin, “Stable Parametric Identification of Vibratory Diagnostics Objects”, Journal of Vibroengineering, 10:2 (2008), 142–146

[17] A. N. Tvrsin, A. A. Azaryan, “Exact Algorithms for Implementation of the Least Absolute Deviations' Method Based on the Descent Through the Nodal Straight Lines”, BSU Bulletin. Mathematics, Informatics, 2017, no. 4, 21–32 (in Russ.) | MR