Unable to resolve the warning on ill conditioned Jacobian
I want to fit my data (1st column: x , 2nd column: y, given in the text file) to a sigmoidal function using the given function file (sigm_fit_base_e.m) The function is the standard matlab function which I modified from base 10 to base e and increased the maxIter to 10000. My initial guess parameters are:
[0 0.2845 9.88 -1] and there are no fixed parameters.
Relevant code lines are:
fPar = sigm_fit_base_e(x,y,[],[0 0.2845 9.88 -1],0);
I get the following warning:
Warning: The Jacobian at the solution is ill-conditioned, and some model parameters may not be estimated well (they are not identifiable). Use caution in making predictions.
> In nlinfit (line 384)
In sigm_fit_base_e (line 130)
I checked all the related answers in the Matlab community and tried to play around by modifiying the initial guess parameters and fixing the 2nd parameter but the warning still persists. Could you please help me fix this warning?I want to fit my data (1st column: x , 2nd column: y, given in the text file) to a sigmoidal function using the given function file (sigm_fit_base_e.m) The function is the standard matlab function which I modified from base 10 to base e and increased the maxIter to 10000. My initial guess parameters are:
[0 0.2845 9.88 -1] and there are no fixed parameters.
Relevant code lines are:
fPar = sigm_fit_base_e(x,y,[],[0 0.2845 9.88 -1],0);
I get the following warning:
Warning: The Jacobian at the solution is ill-conditioned, and some model parameters may not be estimated well (they are not identifiable). Use caution in making predictions.
> In nlinfit (line 384)
In sigm_fit_base_e (line 130)
I checked all the related answers in the Matlab community and tried to play around by modifiying the initial guess parameters and fixing the 2nd parameter but the warning still persists. Could you please help me fix this warning? I want to fit my data (1st column: x , 2nd column: y, given in the text file) to a sigmoidal function using the given function file (sigm_fit_base_e.m) The function is the standard matlab function which I modified from base 10 to base e and increased the maxIter to 10000. My initial guess parameters are:
[0 0.2845 9.88 -1] and there are no fixed parameters.
Relevant code lines are:
fPar = sigm_fit_base_e(x,y,[],[0 0.2845 9.88 -1],0);
I get the following warning:
Warning: The Jacobian at the solution is ill-conditioned, and some model parameters may not be estimated well (they are not identifiable). Use caution in making predictions.
> In nlinfit (line 384)
In sigm_fit_base_e (line 130)
I checked all the related answers in the Matlab community and tried to play around by modifiying the initial guess parameters and fixing the 2nd parameter but the warning still persists. Could you please help me fix this warning? jacobian ill conditioned sigmoidal fit nlinfit MATLAB Answers — New Questions