Abstract
Obtaining polynomial fittings from observational data in two and three dimensions is an interesting and practical task. Such an arduous problem suggests the development of an automatic code. The main novelty we provide lies in the generalization of the classical least squares method in three FORTRAN 77 programs usable in any sampling problem. Furthermore, we introduce the orthogonal 2D-Legendre function in the fitting process. These FORTRAN 77 programs are equipped with the options to calculate the approximation quality standard indicators, obviously generalized to two and three dimensions (correlation nonlinear factor, confidence intervals, cuadratic mean error, and so on). The aim of this paper is to rectify the absence of fitting algorithms for more than one independent variable in mathematical libraries.
Citation Formats
Sanchez-Miro, J J, and Sanz-Martin, J C.
Fitting of two and three variate polynomials from experimental data through the least squares method; Ajuste de polinomios en dos y tres variables independientes por el mtodo de mnimos cuadrados.
Spain: N. p.,
1994.
Web.
Sanchez-Miro, J J, & Sanz-Martin, J C.
Fitting of two and three variate polynomials from experimental data through the least squares method; Ajuste de polinomios en dos y tres variables independientes por el mtodo de mnimos cuadrados.
Spain.
Sanchez-Miro, J J, and Sanz-Martin, J C.
1994.
"Fitting of two and three variate polynomials from experimental data through the least squares method; Ajuste de polinomios en dos y tres variables independientes por el mtodo de mnimos cuadrados."
Spain.
@misc{etde_10104732,
title = {Fitting of two and three variate polynomials from experimental data through the least squares method; Ajuste de polinomios en dos y tres variables independientes por el mtodo de mnimos cuadrados}
author = {Sanchez-Miro, J J, and Sanz-Martin, J C}
abstractNote = {Obtaining polynomial fittings from observational data in two and three dimensions is an interesting and practical task. Such an arduous problem suggests the development of an automatic code. The main novelty we provide lies in the generalization of the classical least squares method in three FORTRAN 77 programs usable in any sampling problem. Furthermore, we introduce the orthogonal 2D-Legendre function in the fitting process. These FORTRAN 77 programs are equipped with the options to calculate the approximation quality standard indicators, obviously generalized to two and three dimensions (correlation nonlinear factor, confidence intervals, cuadratic mean error, and so on). The aim of this paper is to rectify the absence of fitting algorithms for more than one independent variable in mathematical libraries.}
place = {Spain}
year = {1994}
month = {Dec}
}
title = {Fitting of two and three variate polynomials from experimental data through the least squares method; Ajuste de polinomios en dos y tres variables independientes por el mtodo de mnimos cuadrados}
author = {Sanchez-Miro, J J, and Sanz-Martin, J C}
abstractNote = {Obtaining polynomial fittings from observational data in two and three dimensions is an interesting and practical task. Such an arduous problem suggests the development of an automatic code. The main novelty we provide lies in the generalization of the classical least squares method in three FORTRAN 77 programs usable in any sampling problem. Furthermore, we introduce the orthogonal 2D-Legendre function in the fitting process. These FORTRAN 77 programs are equipped with the options to calculate the approximation quality standard indicators, obviously generalized to two and three dimensions (correlation nonlinear factor, confidence intervals, cuadratic mean error, and so on). The aim of this paper is to rectify the absence of fitting algorithms for more than one independent variable in mathematical libraries.}
place = {Spain}
year = {1994}
month = {Dec}
}