NoobixCube
Nov2-08, 04:48 PM
Hey all,
just wondering if you can help me out. I am using 'fminsearch' function in MATLAB 7.4.0 R2007a to fit data.
But 'fminsearch' is a nonlinear optimisation routine and hence has no concept of errors on data points. I have been told to weight my data points with the following function:
w_{i}=1/e_{i}
such that e is the internal error of the data at that point in time.
How do I implement this in my code?
Any suggestions will be most helpful.
just wondering if you can help me out. I am using 'fminsearch' function in MATLAB 7.4.0 R2007a to fit data.
But 'fminsearch' is a nonlinear optimisation routine and hence has no concept of errors on data points. I have been told to weight my data points with the following function:
w_{i}=1/e_{i}
such that e is the internal error of the data at that point in time.
How do I implement this in my code?
Any suggestions will be most helpful.