r of points averaged for this xk.
And "sig" should give you some information on errors...
HTH
Denis
De : users De la part de CRETE Denis
Envoyé : mardi 25 août 2020 16:38
À : Users mailing list for Scilab ; Heinz Nabielek
Objet : Re: [Scilab-users] errors (uncertainties) in non-linear lea
) in non-linear least-squares
fitting parameters
In that case, the code can be simplified using backslash left matrix division:
// Fixed point (-4,0) solution:
a = (MW+4)\Y;
b = a*4;
GG= a'.*.xx' + repmat(b',1,size(xx,1));
plot(xx,GG','LineWidth',1);
Regards,
Rafael
On 24.08.2020, at 23:08, Rafael Guerra wrote:
>
> Hi Heinz,
>
> For the regression errors, I am not an expert but from wikipedia or from
> reference below, I would risk the following code (at your peril):
> https://pages.mtu.edu/~fmorriso/cm3215/UncertaintySlopeInterceptOfLeastSquaresFit.pdf
In that case, the code can be simplified using backslash left matrix division:
// Fixed point (-4,0) solution:
a = (MW+4)\Y;
b = a*4;
GG= a'.*.xx' + repmat(b',1,size(xx,1));
plot(xx,GG','LineWidth',1);
Regards,
Rafael
___
users mailing list
Hi Heinz,
For the regression errors, I am not an expert but from wikipedia or from
reference below, I would risk the following code (at your peril):
https://pages.mtu.edu/~fmorriso/cm3215/UncertaintySlopeInterceptOfLeastSquaresFit.pdf
// Note: for degrees of freedom>=6, t-distribution ~2
N =
I have successfully fitted straight lines to my avian mortality Monte-Carlo
simulation model (function of turbine size and wind speed distributions):
f(x) = pi (x+p4) with p1 for 7, p2 for 6 and p3 for 5 m/s mean wind speed
p1 = 0.3930457
p2 = 0.3492537
p3 = 0.2987269
p4 =