Geodesic
On applying Monte Carlo methods to analysis of nonlinear regression models
Sibirskij žurnal vyčislitelʹnoj matematiki, Tome 18 (2015) no. 4, pp. 425-434.

Voir la notice de l'article provenant de la source Math-Net.Ru

This paper presents a criterium, called the coefficients stability for inaccuracy in determining the coefficients of nonlinear regression models describing inexact data. A`method for the coefficients stability estimation is also described. The proposed criterium is illustrated by a computational experiment with the data obtained by measurements of a refractive index dependence on the wavelength in 400–1000 nm band for a transparent polymer. The convergence of the proposed criterium to the known analytical solution for the case of linear regression is also studied. 
@article{SJVM_2015_18_4_a6,
     author = {G. I. Rudoy},
     title = {On applying {Monte} {Carlo} methods to analysis of nonlinear regression models},
     journal = {Sibirskij \v{z}urnal vy\v{c}islitelʹnoj matematiki},
     pages = {425--434},
     publisher = {mathdoc},
     volume = {18},
     number = {4},
     year = {2015},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/SJVM_2015_18_4_a6/}
}
TY  - JOUR
AU  - G. I. Rudoy
TI  - On applying Monte Carlo methods to analysis of nonlinear regression models
JO  - Sibirskij žurnal vyčislitelʹnoj matematiki
PY  - 2015
SP  - 425
EP  - 434
VL  - 18
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/SJVM_2015_18_4_a6/
LA  - ru
ID  - SJVM_2015_18_4_a6
ER  - 
%0 Journal Article
%A G. I. Rudoy
%T On applying Monte Carlo methods to analysis of nonlinear regression models
%J Sibirskij žurnal vyčislitelʹnoj matematiki
%D 2015
%P 425-434
%V 18
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/SJVM_2015_18_4_a6/
%G ru
%F SJVM_2015_18_4_a6
G. I. Rudoy. On applying Monte Carlo methods to analysis of nonlinear regression models. Sibirskij žurnal vyčislitelʹnoj matematiki, Tome 18 (2015) no. 4, pp. 425-434. http://geodesic.mathdoc.fr/item/SJVM_2015_18_4_a6/

[1] Davidson J. W., Savic D. A., Walters G. A., “Symbolic and numerical regression: experiments and applications”, Developments in Soft Computing, 9, eds. John Robert, Birkenhead Ralph, Physica Verlag, Heidelberg, Germany, 2001, 175–182 | DOI

[2] Sammut C., Webb G. I., “Symbolic Regression”, Encyclopedia of Machine Learning, eds. C. Sammut, G. I. Webb, Springer-Verlag, Berlin, 2010 | DOI | Zbl

[3] Strijov V., Weber G. W., “Nonlinear regression model generation using hyperparameter optimization”, Mathematics with Applications, 60:4 (2010), 981–988 | DOI | MR | Zbl

[4] Strijov V. V., Metody induktivnogo porozhdeniya regressionnykh modelej, Preprint, VTs RAN im. A. A. Dorodnitsyna, Moskva, 2008

[5] Rudoy G. I., Strijov V. V., “Algoritmy induktivnogo porozhdeniya superpozitsij dlya approksimatsii izmeryaemykh dannykh”, Informatika i ee primeneniya, 7:1 (2013), 44–53

[6] Vatutin V. A., Ivchenko G. I., Medvedev Yu. I., Chistyakov V. P., Teoriya veroyatnostej i matematicheskaya statistika v zadachakh, Izd-nie 3, Drofa, M., 2005

[7] Marquardt D. W., “An algorithm for least-squares estimation of non-linear parameters”, J. of the Society of Industrial and Applied Mathematics, 11:2 (1963), 431–441 | DOI | MR | Zbl

[8] More J. J., “The Levenberg-Marquardt algorithm: Implementation and theory”, Numerical Analysis, Lect. Notes in Mathematics, 630, ed. G. A. Watson, Springer-Verlag, Berlin, 1978, 105–116 | DOI | MR

[9] Pearson K., “On lines and planes of closest fit to systems of points in space”, Philosophical Magazine, 2:6 (1901), 559–572 | DOI | Zbl