Control Systems and Computers

https://doi.org/10.15407/csc.2022.04.047

Control Systems and Computers, 2022, Issue 4 (300), pp. 47-53

UDC 519.816

Babak Oleh V., PhD (Engineering), Senior Researcher of the Ecological Digital Systems Department, International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, 40, Academician Glushkov av., Kyiv, 03187, Ukraine, ORCID: https://orcid.org/0000-0002-7451-3314, E-mail: dep115@irtc.org.ua, babak@irtc.org.ua

Tatarinov Olexiy E., Researcher of the Ecological Digital Systems Department, International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, 40, Academician Glushkov av., Kyiv, 03187, Ukraine, ORCID: https://orcid.org/0000-0001-7206-6859, E-mail: dep115@irtc.org.ua, al.ed.tatarinov@gmail.com

Sieriebriakov Artem K., PhD Student, Researcher of Intellectual Control Department, International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, 40, Academician Glushkov av., Kyiv, 03187, Ukraine, ORCID: https://orcid.org/0000-0003-3189-7968, E-mail: sier.artem1002@outlook.com

Yakovenko Ivan M., Researcher of Intellectual Automatic Systems Department, International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, 40, Academician Glushkov av., Kyiv, 03187, Ukraine, ORCID: https://orcid.org/0000-0002-4477-3254, E-mail: yakvan@ukr.net

THE QUASI-ORTHOGONALIZATION APPROACH TO SOLVING THE MULTICOLLINEARITY PROBLEM OF EMPIRICAL DATA

This article proposes an approach to solving the problem of regressors multicollinearity using the procedure of quasi-orthogonalization of data. The specified approach is based on the transformation of factors during their coding according to the rules of a full factorial experiment. It is shown that the proposed coding of factors leads to a reduction of multicollinearity of the data. This approach can be used both for building models based on short samples and for batch processing of Big Data.

 Download full text! (On English)

Keywords: multicollinearity problem, quasi-orthogonalization procedure, coding of input data, full factorial experiment.

1. Draper, N., Smith, H., 2007. Applied Regression Analysis, Transl. from English, M.: Publishing house “Williams”, 912 p. (In Russian).
2. Magnus, Ya.R., Katyshev, P.K., Peresetskiy, A.A., 2004. Econometrics, Initial course: Textbook, 6th ed., Rev. and add, Moscow: Delo, 576 p. (In Russian).
3. Zagoruyko, N.G., 1999. Prikladnyye metody analiza dannykh i znaniy, Novosibirsk: IM SO RAN, 270 p. (In Russian).
4. Zagoruyko, N.G., al., 2013. “Obnaruzheniye zakonomernostey v massivakh eksperimental’nykh dannykh”, Vychislitel’nyye tekhnologii, Vol.18, Spetsial’nyy vypusk, pp. 12-20. (In Russian).
5. Gritsenko, V.I., Surovtsev, I.V., Babak, O.V., 2021. “Peculiarities of interconnection 5G, 6G networks with Big Data, Internet of Things and Artificial Intelligence”, Cybernetics and computer engineering, No. 2 (204), pp. 5-19.  (In Ukrainian).
   https://doi.org/10.15407/kvt204.02.005
6. Orlova, I.V., 2019. “The approach to solving the problem of multicollinearity by using the transformation of variables”, Fundamental research, No. 5. [online]. Available at: <https://s.fundamental-research.ru/pdf/2019/5/42464.pdf> (Last accessed: 23 December 2021). (In Russian).
7. Orlova, I.V., 2019. “Korrektirovka spetsifikatsii modeli mnozhestvennoy regressii pri nalichii mul’tikollinearnosti iskhodnykh regressorov”, V knige: Upravleniye razvitiyem krupnomasshtabnykh sistem (MLSD’2019), Materialy Dvenadtsatoy mezhdunar. Conference, Oct. 1-3, 2019, Moskva, Nauchnoye elektronnoye izdaniye, M.: IPU RAN, p. 993-995. [online]. Available at: <http://www.spsl.nsc.ru/FullText/konfe/MLSD_2019.pdf> (Last accessed: 23 December 2021) (In Russian).
8. Adler,V., Markova, Ye.V., Granovskiy, Yu.V., 1976. Planirovaniye eksperimenta pri poiske optimalnykh usloviy [Planning an experiment when searching for optimal conditions], Monograph, M.: Nauka, 280 p. [online] Available at: <http://techliter.ru/load/uchebniki_posobya_lekcii/professionalnaya_literatura/planirovanie_ehksperimenta_pri_poiske_optimalnykh_uslovij_adler_ju_p_markova_e_v_granovskij_ju_v/67-1-0-2759> (Last accessed : January 12, 2022). (In Russian).
9. Kobzar, A.I., 2006. Applied mathematical statistics, For engineers and scientists, Moscow: FIZMATLIT Publ., 816 p. (In Russian).

Received 19.01.2022