Re: Switch Axis?

*To*: mathgroup at christensen.cybernetics.net*Subject*: [mg1073] Re: Switch Axis?*From*: rubin at msu.edu (Paul A. Rubin)*Date*: Fri, 12 May 1995 17:21:00 -0400*Organization*: Michigan State University

In article <3ohk87$5k2 at news0.cybernetics.net>, chris at canada.medchem.purdue.edu (chris) wrote: [snip] ->I was also trying to do nonlinearfitting to the following group of data: ->{0.5, 0.001}, {0.15, 0.005}, {0.1, 0.01}, {0.01, 0.1}, {0.001, 0.5} ->The function -> 1-1/(1+0.00065/x) ->produces a curve (use LogPlot[1-1/(1+0.00065/x), {x, 0.001,1 }) that seems ->to fit the data. However, when I used NonLinearFit with this function, I ->got the message that the function does not match a real number when ->x=0.001. ->Could someone help me on these two problems? Thanks a lot! I would guess you had a syntax error. NonlinearFit worked ok when I used models with either one or two coefficients to be fitted (you didn't specify which coefficients were symbolic in your model): data = {{0.5,0.001}, {0.15, 0.005}, {0.1, 0.1}, {0.01, 0.1}, {0.001, 0.5}}; NonlinearFit[ data, 1-1/(a+b/x), x, {a, b} ] (* fit two coeffs *) {a -> 1.02788, b -> 0.000938836} NonlinearFit[ data, 1-1/(1+b/x), x, {b} ] (* fit one coeff *) {b -> 0.000981788} Paul ************************************************************************** * Paul A. Rubin Phone: (517) 432-3509 * * Department of Management Fax: (517) 432-1111 * * Eli Broad Graduate School of Management Net: RUBIN at MSU.EDU * * Michigan State University * * East Lansing, MI 48824-1122 (USA) * ************************************************************************** Mathematicians are like Frenchmen: whenever you say something to them, they translate it into their own language, and at once it is something entirely different. J. W. v. GOETHE