Estimation of linear regression parameters by minimizing the sum of the excesses of the approximation error modules relative to a given level
https://doi.org/10.21822/2073-6185-2025-52-1-105-112
Abstract
Objective. Development of an algorithmic method for estimating the parameters of a linear regression model based on minimizing the sum of excesses of absolute deviations of the calculated values of the dependent variable from the real ones relative to some predetermined level.
Methods. The least absolute values method based on minimizing the city (Manhattan) distance between the vectors of calculated and specified values of the dependent variable is used as a basic method for identifying unknown parameters of the regression equation. Implementation of the method is reduced to a linear programming problem. The problem of minimizing the sum of excesses of absolute deviations of the calculated values of the dependent variable from the real ones relative to some predetermined level is reduced to this problem by introducing some additional constraints and replacing the objective function.
Result. Three alternative, highly adequate, versions of a regression single-factor model for the development of the Russian industrial sector engaged in the production of electrical, electronic and optical equipment are constructed. The volume of investments in the industry is used as an independent variable.
Conclusion. A criterion for the adequacy of regression models is proposed, which is a modification of the loss function used in the least absolute value method.
About the Authors
S. I. Noskov
Irkutsk State Transport University
Russian Federation
Russian Federation
Sergey I. Noskov, Dr. Sci. (Eng), Prof., Prof.,Department of Information Technologies and Information Security,
15 Chernyshevskogo St., Irkutsk 664074
S. V. Belyaev
Irkutsk State Transport University
Russian Federation
Russian Federation
Sergey V. Belyaev, Master's student, Department of Information Technologies and Information Security,
15 Chernyshevskogo St., Irkutsk 664074
References
1. David I.J., Adubisi O.D., Ogbaji O.E., Eghwerido J.T., Umar Z.A. Resistant measures in assessing the adequacy of regression models. Scientific African. 2020; 8. https://doi.org/10.1016/j.sciaf.2020.e00437.
2. Rafaella L. S. do Nascimento, Roberta A. de A. Fagundes, Renata M. C. R. de Souza & Francisco José A. Cysneiros. Interval regression model adequacy checking and its application to estimate school dropout in Brazilian municipality educational scenario. Pattern Analysis and Applications. 2022; 26: 39–59. https://doi.org/10.1007/s10044-022-01093-0.
3. Gongming S., Jiang D., Zhihua S., Zhongzhan Z. Checking the adequacy of functional linear quantile regression model. Journal of Statistical Planning and Inference. 2021; 210: 64-75. https://doi.org/10.1016/j.jspi.2020.05.003.
4. Horvath S., Soot M., Zaddach S., Neuner H., Weitkamp A. Deriving adequate sample sizes for ANN-based modeling of real estate valuation tasks by complexity analysis. Land Use Policy. 2021;107. https://doi.org/10.1016/j.landusepol.2021.105475.
5. McCoach D. B., Newton S. D., Gambino A. J. Multilevel Model Selection: Balancing Model Fit and Adequacy. Methodology for Multilevel Modeling in Educational. Singapore: Springer, 2022.
6. Taherinia M., Baqeri A. The Effect of Capital Adequacy Ratio on the Ratio of the Bank Reserves Accepted in the Tehran Stock Exchange. International Journal of Economics and Financial Issues. 2018;8(1):161- 167. https://www.econjournals.com/index.php/ijefi/article/view/5911.
7. Rubbaniy G., Khalid A.A., Polyzos S., Almessabi B.N. Cyclicality of capital adequacy ratios in heterogeneous environment: A nonlinear panel smooth transition regression explanation. Managerial and Decision Economics. 2021; 43(6): 1960-1979. https://doi.org/10.1002/mde.3502.
8. Krätschmer V. Nonasymptotic Upper Estimates for Errors of the Sample Average Approximation Method to Solve Risk-Averse Stochastic Programs. SIAM Journal on Optimization. 2024;34(2):1264-1294. https://doi.org/10.1137/22M1535425.
9. Alkatsev M.I., Alkatsev V.M., Abaev Z.K., Dzgoev A.E. Evaluation of the adequacy of mathematical models of metallurgical processes within the framework of regression analysis of data in the MathCad package. Bulletin of the South Ural State University. Series: Metallurgy. 2020; 20(3): 12-20. (In Russ.).
10. Krotov S.V., Krotov V.P. Efficiency of response surface regression in analyzing the bearing capacity of a wagon wheel pair. Scientific problems of transport in Siberia and the Far East. 2010; (2): 143-146. (In Russ.).
11. Kuznetsova O.A., Rozenzweig A.I. Regression analysis of the influence of the main performance indicators of Russian universities on the number of online courses. Bulletin of the Moscow Financial and Law University MFUA. 2019; (4): 182-188. (In Russ.).
12. Zolin P.P., Lebedev V.M., Konvay V.D. Mathematical modeling of biochemical processes using regression analysis Omsk: Publishing house of Omsk State University, 2009. 344 p. (In Russ.).
13. Virstyuk A.Yu., Mishina V.S. Application of regression analysis to assess the performance of oil wells with paraffin oil. Bulletin of Tomsk Polytechnic University. Georesources Engineering. 2020; 331(1): 117-124. (In Russ.).
14. Ivanishchev Yu.G., Davydov V.M., Sarygin A.V. Comparative analysis of the calculated parameters of the regression model depending on the sample size and the method of calculating variances. Bulletin of the Pacific State University. 2022;2(65):51-60. (In Russ.).
15. Noskov S.I. Method of resolving alternativeness in estimating parameters of regression models. Models, systems, networks in economics, technology, nature and society. 2023;4(48):154-162. (In Russ.).
16. Pardoe I. Applied Regression Modeling. John Wiley & Sons, Inc., 2021.
17. Noskov S.I. Minimization of the average and maximum relative errors of approximation of the regression model. Bulletin of Tula State University. Engineering sciences. 2023;(1): 340-343.
18. Noskov S.I. On data clustering based on the properties of linear regression parameter identification methods. Information technologies and mathematical modeling in complex systems management. 2022;4(16): 82-85. (In Russ.).
19. Industry of Russia 2010: Statistical Collection. Moscow: Rosstat, 2010:453 p. (In Russ.).
20. Industrial Production in Russia. 2016: Statistical Collection. Moscow: Rosstat, 2016: 347 p. (In Russ.).
21. Industrial production in Russia. 2019: Statistical collection. Moscow: Rosstat, 2019:286 p. (In Russ.).
22. Industrial production in Russia. 2023: Statistical collection. Moscow: Rosstat, 2023:259 p. (In Russ.).
23. Industrial production. Rosstat. (In Russ.). URL: https://rosstat.gov.ru/enterprise_industrial (accessed: 18.09.2024).
Review
For citations:
Noskov S.I., Belyaev S.V. Estimation of linear regression parameters by minimizing the sum of the excesses of the approximation error modules relative to a given level. Herald of Dagestan State Technical University. Technical Sciences. 2025;52(1):105-112. (In Russ.) https://doi.org/10.21822/2073-6185-2025-52-1-105-112
Views:
53
Email this article 
