Least square fitting with one parameter less
arXiv:1505.07564 · doi:10.1016/j.cpc.2015.09.021
Abstract
It is shown that whenever the multiplicative normalization of a fitting function is not known, least square fitting by $Ï^2$ 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.
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