Abstract
This paper presents a criterion, called coefficient stability, for determining errors in the coefficients of nonlinear regression models describing inexact data. A method for the estimation of coefficient stability is also described. The criterion is illustrated by a computational experiment with data obtained by measuring the refractive index as a function of the wavelength in the 400–1000 nm band for a transparent polymer. The convergence of the criterion to a known analytical solution for the case of linear regression is also studied.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Davidson, J.W., Savic, D.A., and Walters, G.A., Symbolic and Numerical Regression: Experiments and Applications, Develop. Soft Computing, 2001, vol. 9, pp. 175–182.
Sammut, C. and Webb, G.I., Symbolic Regression, Encyclopedia of Machine Learning, Berlin: Springer-Verlag, 2010; http://dxdoiorg/10.1007/978-0-387-30164-8.
Strijov, V. and Weber, G.W., Nonlinear Regression Model Generation Using Hyperparameter Optimization, Math. Appl., 2010, vol. 60, no. 4, pp. 981–988, http://dxdoiorg/10.1016/jcamwa.2010.03.021.
Strizhov, V.V., Methods of Inductive Generation of Regression Models, Preprint of the DorodnitsynComputing Center, Russ. Acad. Sci., Moscow, 2008.
Rudoy, G.I. and Strizhov, V.V., Algorithms for Inductive Generation of Superpositions for Approximation of Experimental Data, Inform. Appl., 2013, vol. 7, no. 1, pp. 44–53.
Vatutin, V.A., Ivchenko, G.I., Medvedev, Yu.I., and Chistyakov, V.P., Teoriya veroyatnostei i matematicheskaya statistika v zadachakh (Probability Theory and Mathematical Statistics in Exercises), 3rd ed., Moscow: Drofa, 2005.
Marquardt, D.W., An Algorithm for Least-Squares Estimation of Non-Linear Parameters, J. Soc. Industr. Appl.Math., 1963, vol. 11, no. 2, pp. 431–441.
More, J.J., The Levenberg–Marquardt Algorithm: Implementation and Theory, Numerical Analysis, Lect. Notes Math. 1978, vol. 630, pp. 105–116.
Pearson, K., On Lines and Planes of Closest Fit to Systems of Points in Space, Philos. Mag., 1901, vol. 2, no. 6, pp. 559–572.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © G.I. Rudoy, 2015, published in Sibirskii Zhurnal Vychislitel’noi Matematiki, 2015, Vol. 18, No. 4, pp. 425–434.
Rights and permissions
About this article
Cite this article
Rudoy, G.I. Applying Monte Carlo methods to analysis of nonlinear regression models. Numer. Analys. Appl. 8, 344–350 (2015). https://doi.org/10.1134/S1995423915040072
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1995423915040072