Hello, The function gsl_multifit_linear_svd computes the fit residuals in order to compute chi^2, but I was thinking it might be useful to have a separate function to compute the residuals vector since its often useful for the user to look at all the residuals as a measure of quality of fit. So basically just reproduce lines 158-166 of multilinear.c in a new function and store the residuals in a user supplied vector. Anyone disagree?
Patrick Alken
