Receipt date: 
01.06.2020
Year: 
2020
Journal number: 
УДК: 
519.862.6
DOI: 

10.26731/2658-3704.2020.2(7).1-13

Article File: 
Pages: 
1
13
Abstract: 

In this paper, we study the possibility of using linear pair models with parameters in the form of linear operators matrices of a two-dimensional vector space in practice. A detailed description of these models, a method for estimating them, and a forecasting algorithm for them are given. To automate the process of constructing such models using the Gretl econometric package, a special script was developed that modeled the freight turnover of Russian railway transport and extrapolated its future and past values. For certain sample sizes, the resulting models turned out to be much more adequate than conventional paired linear regression models. On the basis of the study, the sample sizes were established for which it is advisable to build linear pair models with parameters in the form of linear operators matrices of a two-dimensional vector space.

List of references: 

1. Harrell Jr., Frank E. Regression modeling strategies: with applications to linear models, logistic and ordinal regression, and survival analysis. 2nd edition. Springer Series in Statistics, 2015. 607 p.

2. Mendenhall W., Sincich T.T. A second course in statistics: regression analysis. 8th edition. Pearson, 2019. 848 p.

3. Darlington R.B., Hayes A.F. Regression analysis and linear models: concepts, applications, and implementations. The Guilford Press, 2016. 661 p.

4. Noskov S.I. Tehnologija modelirovanija ob’ektov s nestabil'nym funkcionirovaniem i neopredelennost'ju v dannyh [Modeling technology for objects with unstable operation and data uncertainty]. Irkutsk, RIC GP «Oblinformpechat'» Publ., 1996. 321 р.

5. Noskov S.I. Metod antirobastnogo otsenivaniya parametrov lineynoy regressii: chislo maksimal'nykh po modulyu oshibok approksimatsii [Method of antirobast estimation of linear regression parameters: number of maximum of the module of approximation errors]. Yuzhno-Sibirskiy nauchnyy vestnik [South Siberian Scientific Bulletin]. 2020, no. 1, vol. 29, pp. 51–54.

6. Noskov S.I. O metode smeshannogo otsenivaniya parametrov lineynoy regressii [About the method of mixed estimation of parameters of linear regression]. Informacionnye tehnologii i matematicheskoe modelirovanie v upravlenii slozhnymi sistemami: ehlektronnyj nauchnyj zhurnal [Information technology and mathematical modeling in the management of complex systems: electronic scientific journal]. 2019, no. 1, vol. 2, pp. 41–45.

7. Noskov S.I., Bazilevskiy M.P. Mnozhestvennoe otsenivanie parametrov i kriteriy soglasovannosti povedeniya v regressionnom analize [Multiple parameter estimation and behavior consistency criterion in regression analysis]. Vestnik Irkutskogo gosudarstvennogo tekhnicheskogo universiteta [Proceedings of ISTU]. 2018, no. 4, vol. 135, pp. 101–110.

8. Noskov S.I., Baenhaeva A.V. Mnozhestvennoe otsenivanie parametrov lineynogo regressionnogo uravneniya [Multiple estimation of parameters for the linear regression equation]. Sovremennye tekhnologii. Sistemnyy analiz. Modelirovanie [Modern technologies. System analisys. Modeling]. 2016, no. 3, vol. 51, pp. 133-138.

9. Baenhaeva A.V., Bazilevskiy M.P., Noskov S.I. Modelirovanie valovogo regional'nogo produkta Irkutskoy oblasti na osnove primeneniya metodiki mnozhestvennogo otsenivaniya regressionnykh parametrov [Modeling of gross regional product Irkutsk region of the basis of methods of multiple estimation of regression parameters]. Fundamental'nye issledovaniya [Fundamental research]. 2016, no. 10-1, pp. 9–14.

10. Bazilevskiy M.P., Noskov S.I. Formalizatsiya zadachi postroeniya lineyno-mul'tiplikativnoy regressii v vide zadachi chastichno-bulevogo lineynogo programmirovaniya [Formalization of the problem of construction of linear multiplicative regressions in the form of a partial-Boolean linear programming problem]. Sovremennye tekhnologii. Sistemnyy analiz. Modelirovanie [Modern technologies. System analisys. Modeling]. 2017, no. 3, vol. 55, pp. 101–105.

11. Ivanova N.K., Lebedeva S.A., Noskov S.I. Identifikatsiya parametrov nekotorykh negladkikh regressiy [Identification of parameters of some nonsmooth regressions]. Informatsionnye tekhnologii i problemy matematicheskogo modelirovaniya slozhnykh system [Information technologies and problems of mathematical modeling of complex systems]. Irkutsk, 2016, vol. 17, pp. 107–110.

12. Noskov S.I., Bazilevskiy M.P. Postroenie regressionnykh modeley s ispol'zovaniem apparata lineyno-bulevogo programmirovaniya [Construction of regression models using linear Boolean programming]. Irkutsk, IrGUPS, 2018. 176 p.

13. Bazilevskiy M.P. Kriterii nelineynosti mnogofaktornykh kvazilineynykh regressiy [Nonlinearity criteria for multivariate quasilinear regressions]. Molodezh' i nauka: aktual'nye problemy fundamental'nykh i prikladnykh issledovaniy [Youth and science: actual problems of fundamental and applied research]. 2019, pp. 210–213.

14. Bazilevskiy M.P. Kriterii nelineynosti kvazilineynykh regressionnykh modeley [Nonlinearity criteria for quasilinear regression models]. Modelirovanie, optimizatsiya i informatsionnye tekhnologii [Modeling, optimization and information technologies]. 2018, no. 4, vol. 23, pp. 185–195.

15. Bazilevskiy M.P. Sintez modeli parnoy lineynoy regressii i prosteyshey EIV-modeli [Synthesis of the paired linear regression model and the simplest EIV model]. Modelirovanie, optimizatsiya i informatsionnye tekhnologii [Modeling, optimization and information technologies]. 2019, no. 1, vol. 24, pp. 170–182.

16. Bazilevskiy M.P. Issledovanie dvukhfaktornoy modeli polnosvyaznoy lineynoy regressii [Study of a two-factor model of fully connected linear regression]. Modelirovanie, optimizatsiya i informatsionnye tekhnologii [Modeling, optimization and information technologies]. 2019, no. 2, vol. 25, pp. 80–96.

17. Bazilevskiy M.P., Vlasenko L.N. Otsenivanie modeley parnoy lineynoy regressii s parametrami v vide matrits lineynykh operatorov dvumernogo vektornogo prostranstva [Estimation of pair linear regression models with parameters in the form of linear operator matrices of two-dimensional vector space]. Modelirovanie, optimizatsiya i informatsionnye tekhnologii [Modeling, optimization and information technologies]. 2010, no. 1, available at: https://moit.vivt.ru/wp-content/uploads/2020/02/BazilevskiySoavtori_1_20... DOI: 10.26102/2310-6018/2020.28.1.015

18. Bazilevskiy M.P., Vrublevskiy I.P., Noskov S.I., Yakovchuk I.S. Srednesrochnoe prognozirovanie ekspluatatsionnykh pokazateley funktsionirovaniya Krasnoyarskoy zheleznoy dorogi [Medium-term forecasting of performance indicators of functioning of Krasnoyarsk railway]. Fundamental'nye issledovaniya [Fundamental research]. 2016, no. 10-3. – pp. 471-476.

19. Bazilevskiy M.P., Gefan G.D. Problema avtokorrelyatsii ostatkov regressii na primere modelirovaniya gruzooborota zheleznodorozhnogo transporta po dannym vremennykh ryadov [The problem of autocorrelation in regression residuals by example of modeling rail freight based on time series data]. Sovremennye tekhnologii. Sistemnyy analiz. Modelirovanie [Modern technologies. System analisys. Modeling]. 2016, no. 1, vol. 49, pp. 141–147.

20. Bazilevskiy M.P. Prognozirovanie gruzooborota zheleznodorozhnogo transporta po regressionnym modelyam s determinirovannymi i stokhasticheskimi ob"yasnyayushchimi peremennymi [Prediction of freight turnover of railway transport using regression models with deterministic and stochastic explanatory variables]. Nauchnye vedomosti Belgorodskogo gosudarstvennogo universiteta. Seriya: Ekonomika. Informatika [Bulletin of BSU. Ser. Economics. Informatics]. 2019, no. 1, pp. 117–129.

.