Least square fitting with one parameter less
Data Analysis, Statistics and Probability
2016-05-03 v2 Statistical Mechanics
High Energy Physics - Lattice
Computational Physics
Abstract
It is shown that whenever the multiplicative normalization of a fitting function is not known, least square fitting by minimization can be performed with one parameter less than usual by converting the normalization parameter into a function of the remaining parameters and the data.
Cite
@article{arxiv.1505.07564,
title = {Least square fitting with one parameter less},
author = {Bernd A. Berg},
journal= {arXiv preprint arXiv:1505.07564},
year = {2016}
}
Comments
6 pages, 1 figure. Fortran code available on the Web. Erratum: The 4-parameter example suffered from a typo in two subroutines, which is now corrected