Try using or tightening upper and lower bounds on coefficients.

8 views (last 30 days)
hello
please i need your help the attatched file is my data and i want to do matlab curve fittining using custom equation:
4.112-k1*exp(-[x-477/m])-k2*exp(-[x-477/d])
i got error as in the title the values in the equation based on knowledge from data itself as paramters that already know and i want to know the other coffecient of the equation .. i have tried many methods and reducing using different algorithm using command but i still get an error please help me with this

Answers (1)

Bjorn Gustavsson
Bjorn Gustavsson on 26 Aug 2019
For arbitrary fitting tasks I personally prefer to use weighted least-square minimization using some optimization function,
if lsqnonlin doesn't work for you you could try the file exchange contributions: fminsearchbnd, minimize. That way I have more direct control of what is done.
HTH

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!