OEFPIL: New Method and Software Tool for Fitting Nonlinear
Functions to Correlated Data With Errors in Variables

D 2023

OEFPIL: New Method and Software Tool for Fitting Nonlinear Functions to Correlated Data With Errors in Variables

ŠLESINGER, Radek; Anna Charvatova CAMPBELL; Zdeňka GERŠLOVÁ; Vojtěch ŠINDLÁŘ; Gejza WIMMER et al.

Základní údaje

Originální název

OEFPIL: New Method and Software Tool for Fitting Nonlinear Functions to Correlated Data With Errors in Variables

Autoři

ŠLESINGER, Radek; Anna Charvatova CAMPBELL; Zdeňka GERŠLOVÁ; Vojtěch ŠINDLÁŘ a Gejza WIMMER

Vydání

New Jersey, Proceedings of the 14th International Conference on Measurement, MEASUREMENT 2023, od s. 126-129, 4 s. 2023

Nakladatel

IEEE

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10103 Statistics and probability

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Odkazy

URL

Označené pro přenos do RIV

Ano

Organizační jednotka

Přírodovědecká fakulta

ISBN

979-8-3503-1218-8

DOI

https://doi.org/10.23919/MEASUREMENT59122.2023.10164444

EID Scopus

2-s2.0-85165022027

Klíčová slova anglicky

Function Fitting; Nonlinear Regression; Errors in Variables; Correlated Data

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 30. 7. 2025 10:42, Mgr. Marie Novosadová Šípková, DiS.

Anotace

V originále

We present a new method, called OEFPIL, as well as its software implementation for nonlinear function fitting to data with errors in variables where correlation, both within variables and among variables, might be present. In principle, OEFPIL can be employed for fitting both explicit and implicit functions of any number of variables. Importantly, apart from the parameter estimates, OEFPIL also yields their covariance matrix, required for further analyses. Multiple comparisons with existing methods on various types of problems, some of which are presented in this paper, have shown excellent agreement between OEFPIL and other methods.

Citovat

ŠLESINGER, Radek; Anna Charvatova CAMPBELL; Zdeňka GERŠLOVÁ; Vojtěch ŠINDLÁŘ a Gejza WIMMER. OEFPIL: New Method and Software Tool for Fitting Nonlinear Functions to Correlated Data With Errors in Variables. In Dvurecenskij A., Svehlikova J., Witkovsky V., Manka J. Proceedings of the 14th International Conference on Measurement, MEASUREMENT 2023. New Jersey: IEEE, 2023, s. 126-129. ISBN 979-8-3503-1218-8. Dostupné z: https://doi.org/10.23919/MEASUREMENT59122.2023.10164444.

@inproceedings{2510426,
   author = {Šlesinger, Radek and Campbell, Anna Charvatova and Geršlová, Zdeňka and Šindlář, Vojtěch and Wimmer, Gejza},
   address = {New Jersey},
   booktitle = {Proceedings of the 14th International Conference on Measurement, MEASUREMENT 2023},
   doi = {https://doi.org/10.23919/MEASUREMENT59122.2023.10164444},
   editor = {Dvurecenskij A., Svehlikova J., Witkovsky V., Manka J.},
   keywords = {Function Fitting; Nonlinear Regression; Errors in Variables; Correlated Data},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {New Jersey},
   isbn = {979-8-3503-1218-8},
   pages = {126-129},
   publisher = {IEEE},
   title = {OEFPIL: New Method and Software Tool for Fitting Nonlinear Functions to Correlated Data With Errors in Variables},
   url = {https://doi.org/10.23919/MEASUREMENT59122.2023.10164444},
   year = {2023}
}

TY  - CONF
ID  - 2510426
AU  - Šlesinger, Radek - Campbell, Anna Charvatova - Geršlová, Zdeňka - Šindlář, Vojtěch - Wimmer, Gejza
PY  - 2023
TI  - OEFPIL: New Method and Software Tool for Fitting Nonlinear Functions to Correlated Data With Errors in Variables
PB  - IEEE
CY  - New Jersey
SN  - 9798350312188
KW  - Function Fitting
KW  - Nonlinear Regression
KW  - Errors in Variables
KW  - Correlated Data
UR  - https://doi.org/10.23919/MEASUREMENT59122.2023.10164444
N2  - We present a new method, called OEFPIL, as well as its software implementation for nonlinear function fitting to data with errors in variables where correlation, both within variables and among variables, might be present. In principle, OEFPIL can be employed for fitting both explicit and implicit functions of any number of variables. Importantly, apart from the parameter estimates, OEFPIL also yields their covariance matrix, required for further analyses. Multiple comparisons with existing methods on various types of problems, some of which are presented in this paper, have shown excellent agreement between OEFPIL and other methods.
ER  -

ŠLESINGER, Radek; Anna Charvatova CAMPBELL; Zdeňka GERŠLOVÁ; Vojtěch ŠINDLÁŘ a Gejza WIMMER. OEFPIL: New Method and Software Tool for Fitting Nonlinear Functions to Correlated Data With Errors in Variables. In Dvurecenskij A., Svehlikova J., Witkovsky V., Manka J. \textit{Proceedings of the 14th International Conference on Measurement, MEASUREMENT 2023}. New Jersey: IEEE, 2023, s.~126-129. ISBN~979-8-3503-1218-8. Dostupné z: https://doi.org/10.23919/MEASUREMENT59122.2023.10164444.

Přehled o publikaci