Determining a piecewise linear trend of a nonstationary time series based on intelligent data analysis. I: Description and substantiation of the method. (English. Ukrainian original) Zbl 07840786
Cybern. Syst. Anal. 60, No. 1, 50-59 (2024); translation from Kibern. Sist. Anal. 60, No. 1, 61-72 (2024).
Summary: The authors propose considering the trend of a non-stationary time series as a linear regression with unknown switching points. The method of evaluating the switching points based on intelligent data analysis using statistical criteria is described and substantiated.
References:
| [1] | Bai, J., Estimation of a change point in multiple regression models, The Review of Economics and Statistics, 79, 4, 551-563 (1977) · doi:10.1162/003465397557132 |
| [2] | Bai, J.; Perron, P., Computation and analysis of multiple structural change models, J. Appl. Econometrics, 18, 1-22 (2003) · doi:10.1002/jae.659 |
| [3] | A. Casini and P. Perron, “Continuous record Laplace-based inference about the break date in structural change models,” J. Econometrics, May, 37-53 (2020). · Zbl 07376505 |
| [4] | Perron, P.; Zorta, E., Estimation and inference of linear trend slope ratios with an application to global temperature, J. Time Series Analysis, 38, 5, 630-667 (2017) · Zbl 1378.62082 |
| [5] | Korkhin, AS, Constructing a switching regression with unknown switching points, Cybern. Syst. Analysis, 54, 3, 443-455 (2018) · Zbl 1401.62109 · doi:10.1007/s10559-018-0045-9 |
| [6] | Knopov, PS; Korkhin, AS, Continuous-time switching regression method with unknown switching points, Cybern. Syst. Analysis, 56, 1, 68-80 (2020) · Zbl 1454.62216 · doi:10.1007/s10559-020-00222-z |
| [7] | Korkhin, AS, An approximate method of constructing a switching regression with unknown switch points, Cybern. Syst. Analysis, 56, 3, 426-438 (2020) · Zbl 1454.62265 · doi:10.1007/s10559-020-00258-1 |
| [8] | Knopov, PS; Korkhin, AS, Statistical analysis of the dynamics of coronavirus cases using stepwise switching regression, Cybern. Syst. Analysis, 56, 6, 943-952 (2020) · doi:10.1007/s10559-020-00314-w |
| [9] | Rozin, BB; Kotyukov, VI; Yagolnitser, MA, Economic and Statistical Models of Variable Structure (1984), Novosibirsk: Nauka, Novosibirsk · Zbl 0567.62095 |
| [10] | N. R. Draper and H. Smith, Applied Regression Analysis, Wiley Ser. In Probability and Statistics, Wiley Interscience (1998). · Zbl 0895.62073 |
| [11] | Seber, J., Linear Regression Analysis [Russian translation] (1980), Moscow: Mir, Moscow · Zbl 0447.62065 |
| [12] | A. Korkhin and Z. Przhebitsyn, Fundamentals of Probability Theory and Mathematical Statistics (for Economists) [in Russian], Lira, Dnipro (2022). |
| [13] | Chow, GC, Tests of equality between sets of coefficients in two linear regressions, Econometrica, 28, 3, 591-605 (1960) · Zbl 0099.14304 · doi:10.2307/1910133 |
| [14] | Albert, A., Regression and the Moore-Penrose Pseudoinverse (1972), New York: Academic Press, New York · Zbl 0253.62030 |
| [15] | P. S. Knopov, A. S. Korkhin, and L. B. Vovk, “On Minimum length confidence intervals,” in: A. A. Gaivoronski, P. S. Knopov, and V. A. Zaslavskyi (eds.), Modern Optimization Methods for Decision Making under Risk and Uncertainty, CRC Press (2023), pp. 87-101. doi:10.1201/9781003260196. · Zbl 07775708 |
| [16] | Korkhin, AS; Minakova, EP, Computer Statistics, Part 2 (2009), Dnipropetrovsk: National Mining University, Dnipropetrovsk |
| [17] | Korkhin, AS, Parameter estimation accuracy for nonlinear regression with nonlinear constraints, Cybern. Syst. Analysis, 34, 5, 663-672 (1998) · Zbl 0968.62525 · doi:10.1007/BF02667038 |
| [18] | A. S. Korkhin, “Solution of problems of the nonlinear least-squares method with nonlinear constraints based on the linearization method,” Probl. Upravl. Inform., No. 6, 124-135 (1998 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
