English

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 χ2\chi^2 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

R2 v1 2026-06-22T09:42:52.562Z