Least squares: Linear and non-linear

Abstract

The use of modern computers affords the instructor an excellent opportunity to introduce highly refined techniques of data treatment.

Improved parameter estimates in drug-protein binding studies by non-linear regression

“…the method of least squares and estimation of parameter uncertainties, then the extra calculations are inconsequential on a computer. Musulin (1973) has shown in viscosity work that linear and non-linear estimates of a given problem may differ, but that these converge with increasing precision of the primary data, in accordance with our results. The implications of this general rule are at variance with a not uncommon experimental attitude.…”

“…Yet these are precisely the type of data which should not be rearranged. In summary, Musulin (1973) states "the use of modern computers affords, . .…”

Quantitative analyses of multicomponent fluorescence data by the methods of least squares and non-negative least sum of errors

“…Recently, Leggett (10) has discussed the application of non-negative linear least squares to the analysis of multicomponent spectral data. Related topics such as linear and nonlinear least squares (11), multiparameter curve fitting (12), and weighting factors (13) in least-squares analyses have also been discussed.…”