Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Purpose. Investigation of multicollinearity in multifactorial economic and mathematical regression models of activity of Inhu lets Mining and Processing Plant and reduction of its negative influence based on application of the parameterization method.Methodology. To reduce the negative impact of multicollinearity in multifactorial regression models, a technique is developed that is based on the transition from the function of several variables to its parametric representation by analyzing the correlation matrix between factors in order to eliminate mutual correlation.findings. Economic and mathematical modeling of the activity of the JSC Inhulets Mining and Processing Combine showed that the presence of multicollinearity when applying a multifactor regression model leads to a distortion of the obtained results, which reduces the practical value of the model. The application of the parametrization method made it possible to reduce the in fluence of multicollinearity by providing parametric representations of the economicmathematical model of holding the real economic process. The application of the parameterization method makes it easier to construct an economicmathematical mod el in the form of regression equations, to reduce the negative impact of multicollinearity in the implementation and meaningful analysis of features of economic and mathematical modeling using multivariate regression equations. originality. For the first time, the application of the parameterization method is proposed, which allows us to simplify the construction of an economicmathematical model in the form of regression equations. Using the parameterization method allows reducing the uncertainty in the synthesis of multivariate regression equations, ensuring appropriate adequacy.Practical value. The analysis of the obtained results of economic and mathematical modeling of the activity of the Inhulets Mining and Processing Plant based on significant statistical material using the developed algorithm of elimination of multicol linearity confirmed the effectiveness of the proposed approach. It is recommended to include the developed algorithm for elimina tion of multicollinearity by parametrization in the practice of management of economic activity of mining enterprises.
Purpose. Investigation of multicollinearity in multifactorial economic and mathematical regression models of activity of Inhu lets Mining and Processing Plant and reduction of its negative influence based on application of the parameterization method.Methodology. To reduce the negative impact of multicollinearity in multifactorial regression models, a technique is developed that is based on the transition from the function of several variables to its parametric representation by analyzing the correlation matrix between factors in order to eliminate mutual correlation.findings. Economic and mathematical modeling of the activity of the JSC Inhulets Mining and Processing Combine showed that the presence of multicollinearity when applying a multifactor regression model leads to a distortion of the obtained results, which reduces the practical value of the model. The application of the parametrization method made it possible to reduce the in fluence of multicollinearity by providing parametric representations of the economicmathematical model of holding the real economic process. The application of the parameterization method makes it easier to construct an economicmathematical mod el in the form of regression equations, to reduce the negative impact of multicollinearity in the implementation and meaningful analysis of features of economic and mathematical modeling using multivariate regression equations. originality. For the first time, the application of the parameterization method is proposed, which allows us to simplify the construction of an economicmathematical model in the form of regression equations. Using the parameterization method allows reducing the uncertainty in the synthesis of multivariate regression equations, ensuring appropriate adequacy.Practical value. The analysis of the obtained results of economic and mathematical modeling of the activity of the Inhulets Mining and Processing Plant based on significant statistical material using the developed algorithm of elimination of multicol linearity confirmed the effectiveness of the proposed approach. It is recommended to include the developed algorithm for elimina tion of multicollinearity by parametrization in the practice of management of economic activity of mining enterprises.
Purpose. Improvement of regression economic-mathematical models taking into account the influence of residual error as a random variable. Methodology. Methods of economic-mathematical modeling, regression analysis are used. The real conditional law of distribution of residual error as a complete characteristic of a random variable is applied. Findings. A scientific and practical approach to economic and mathematical modeling based on the study on residual error, to improve the construction of regression equations. Originality. For the first time, the application of residual error analysis as a random variable has been proposed in order to construct its conditional differential distribution function, which allows improving the quality of economic-mathematical modeling in the form of regression equations. The use of the proposed method of taking into account the residual error allows eliminating the negative impact of the violation of the conditions of the properties of the residual error in the implementation of economic and mathematical modeling using regression equations. Practical value. The analysis of the obtained results of economic-mathematical modeling of economic activity of Inhulets Mining and Processing Plant on significant statistical material with the use of the developed algorithm of residual error research confirmed the effectiveness of the proposed approach. It is recommended to include the developed algorithm taking into account the properties of the residual error in the practice of managing the financial activities of mining enterprises.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.