Re: weighted residuals are not real

[Preeti Gaikwad]

On 18 November 2011 15:42, Ben Abbott <address@hidden> wrote:

On Nov 18, 2011, at 9:26 AM, Preeti Gaikwad wrote:

> hi ben I dont hv this dFdp but i think its just differentiation of dp isnt it?

Ok. I'm used to the Matlab approach. My mistake.

I've run your example, but did not encounter any error. I've attached the script I ran and the results as an Octave mat-file (contains the variables "ls", "la", and "fit").

I'm running Octave-3.4.3 with optim-1.0.17.

Ben

Yes this is not giving error but from the fit i can see this is not the best fit what I can see if u plot like that

figure(1)

plot(lambda, ls,'.')

xlabel(' Wavelength [nm]','FontSize',14)

ylabel('Transport m.f.p. [mm]','FontSize',14)

title(' Scattering length from the fit ','FontSize',14)

figure(2)

plot(lambda, la,'r.')

xlabel(' Wavelength [nm]','FontSize',14)

ylabel('Transport m.f.p. [mm]','FontSize',14)

title(' Absorption length from the fit ','FontSize',14)

figure(3)

plot(x,1./T(230,:),'b*')

hold on

plot(x,1./T(450,:),'ro')

plot(x,fit(230,:),'r-')

plot(x,fit(450,:),'b-')

hold off

xlabel(' Thickness L [um]','FontSize',14)

ylabel('1/Transmission [1/%]','FontSize',14)

title(' 1/ Total transmission - lambda cut','FontSize',14)

now to solve this problem and to get best fit I want to remove some points from x and y like from x i want to remove bad points

1.44 1.64 1.71 1.84 1.87 1.95 2.17

total 7 points and same the colum from y

then u see I am getting this error......thanks a lot for ur help and work