ESTIMATING WITH A GIVEN ACCURACY OF THE COEFFICIENTS AT NONLINEAR TERMS OF UNIVARIATE POLYNOMIAL REGRESSION USING A SMALL NUMBER OF TESTS IN AN ARBITRARY LIMITED ACTIVE EXPERIMENT
Keywords:univariate polynomial regression, multivariate polynomial regression, normalized orthogonal polynomials of Forsythe, redundant representation, linear equalities, conditional active experiment
We substantiate the structure of the efficient numerical axis segment an active experiment on which allows finding estimates of the coefficients for
nonlinear terms of univariate polynomial regression with high accuracy using normalized orthogonal Forsyth polynomials with a sufficiently small
number of experiments. For the case when an active experiment can be executed on a numerical axis segment that does not satisfy these conditions, we
substantiate the possibility of conducting a virtual active experiment on an efficient interval of the numerical axis. According to the results of the experiment, we find estimates for nonlinear terms of the univariate polynomial regression under research as a solution of a linear equalities system with
an upper non-degenerate triangular matrix of constraints. Thus, to solve the problem of estimating the coefficients for nonlinear terms of univariate
polynomial regression, it is necessary to choose an efficient interval of the numerical axis, set the minimum required number of values of the scalar
variable which belong to this segment and guarantee a given value of the variance of estimates for nonlinear terms of univariate polynomial regression
using normalized orthogonal polynomials of Forsythe. Next, it is necessary to find with sufficient accuracy all the coefficients of the normalized orthogonal polynomials of Forsythe for the given values of the scalar variable. The resulting set of normalized orthogonal polynomials of Forsythe allows us to estimate with a given accuracy the coefficients of nonlinear terms of univariate polynomial regression in an arbitrary limited active experiment: the range of the scalar variable values can be an arbitrary segment of the numerical axis. We propose to find an estimate of the constant and of
the coefficient at the linear term of univariate polynomial regression by solving the linear univariate regression problem using ordinary least squares
method in active experiment conditions. Author and his students shown in previous publications that the estimation of the coefficients for nonlinear
terms of multivariate polynomial regression is reduced to the sequential construction of univariate regressions and the solution of the corresponding
systems of linear equalities. Thus, the results of the paper qualitatively increase the efficiency of finding estimates of the coefficients for nonlinear
terms of multivariate polynomial regression given by a redundant representation.
Ivahnenko A.G. Modelirovanie Slozhnyh Sistem. Informacionnyj Podhod [Complex Systems Modeling. Informational Approach]. Kiev, Vyshha shkola Publ., 1987. 62 p.
Nastenko E., Pavlov V., Boyko G., Nosovets O. Mnogokriterial'nyj algoritm shagovoj regressii [Multi-criterion step-regression algorithm]. Biomedychna inzheneriya i tekhnolohiya [Biomedical ingeneering and technology]. 2020, no. 3, pp. 48–53. doi: 10.20535/2617- 8974.2020.3.195661
Draper N. R., Smith H. Applied Regression Analysis. 3rd edition. New York: John Wiley & Sons, 1998. 736 p.
Bol'shakov A. A., Karimov R. N. Metody obrabotki mnogomernykh dannykh i vremennykh ryadov: uchebnoe posobie dlya vuzov [Methods for processing multivariate data and time series: textbook for universities]. Moscow: Goryachaya liniya–Telekom, 2007. 522 p.
Shahrel M. Z., Mutalib S., Abdul-Rahman S. PriceCop–Price Monitor and Prediction Using Linear Regression and LSVM-ABC Methods for E-commerce Platform. International Journal of Information Engineering and Electronic Business (IJIEEB), 2021. Vol. 13 (1), pp. 1– 14. doi: 10.5815/ijieeb.2021.01.01
Satter A., Ibtehaz N. A Regression based Sensor Data Prediction Technique to Analyze Data Trustworthiness in Cyber-Physical System. International Journal of Information Engineering and Electronic Business (IJIEEB), 2018. Vol. 10 (3), pp. 15–22. doi: 10.5815/ijieeb.2018.03.03
Isabona J., Ojuh D. O. Machine Learning Based on Kernel Function Controlled Gaussian Process Regression Method for In-depth Extrapolative Analysis of Covid-19 Daily Cases Drift Rates. International Journal of Mathematical Sciences and Computing (IJMSC), 2021. Vol. 7 (2). pp. 14–23. doi: 10.5815/ijmsc.2021.02.02
Babatunde G., Emmanuel A. A., Oluwaseun O. R., Bunmi O. B., Precious A. E. Impact of Climatic Change on Agricultural Product Yield Using K-Means and Multiple Linear Regressions. International Journal of Education and Management Engineering (IJEME), 2019. Vol. 9 (3). pp. 16–26. doi: 10.5815/ijeme.2019.03.02
Pavlov A. A., Kalashnik V. V., Kovalenko D. A. Postroenie mnogomernoj polinomial'noj regressii. Regressija s povtorjajushhimisja argumentami vo vhodnyh dannyh [Multidimensional polynomial regression construction. Regression with duplicate arguments in the input]. Visnyk NTUU “KPI”. Seriya «Informatyka, upravlinnya ta obchislyuvalna tekhnyka» [Visnyk NTUU “KPI”. Informatics, operation and computer science]. Kiev, Vek+ Publ., 2015, no. 62, pp. 57–61
Zgurovsky M. Z., Pavlov A. A. Prinyatie resheniy v setevykh sistemakh s ogranichennymi resursami [Decision making in network systems with limited resources]. Kiev, Nauk. dumka Publ., 2010, 573 p.
Hudson D. J. Statistics Lectures, Volume 2: Maximum Likelihood and Least Squares Theory. CERN Reports 64(18). Geneva, CERN, 1964. (Russ. ed.: Hudson D. Statistika dlja fizikov: Lekcii po teorii verojatnostej i jelementarnoj statistike. Moscow, Mir Publ., 1970. 296 p.). doi: 10.5170/CERN-1964-018
Pavlov A. A., Kalashnik V. V. Rekomendacii po vyboru zony provedenija aktivnogo jeksperimenta dlja odnomernogo polinomial'nogo regressionnogo analiza [Recommendations for choosing the zone of an active experiment for one-dimensional polynomial regression analysis]. Visnyk NTUU “KPI”. Seriya «Informatyka, upravlinnya ta obchislyuvalna tekhnyka» [Visnyk NTUU “KPI”. Informatics, operation and computer science]. Kiev, Vek+ Publ., 2014, no. 60, pp. 41–45.
How to Cite
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).