Least square fitting with one parameter less

Abstract

It is shown that whenever the multiplicative normalization of a fitting function is not known, least square fitting by ${\chi }^2$ 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.

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