[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Help-gsl] nonlinear fit
From: |
Francesco Abbate |
Subject: |
Re: [Help-gsl] nonlinear fit |
Date: |
Wed, 9 Mar 2011 18:09:04 +0100 |
2011/3/8 Irina Stefan <address@hidden>:
> Hi,
>
> This is probably a very easy question, but I'm not very comfortable with gsl,
> so here it goes.
> I'm writing a routine to fit a Gaussian to a set of data points. I'm pretty
> much modifying the example from the gsl manual. However, I want to perform an
> unweighted fit and I'm not sure what function to use as f_i.
Hi,
this is actually an easy question :-)
If you want to perform an unweighted fit just set f_i to Y_i - y_i,
i.e., to the difference between the obsered value and the predicted
one. Just don't forget to do the same thing for f_i and the Jacobian.
In the example they divides by sigma_i so you have just to omit the
division by sigma_i both for f_i and the jacobian.
--
Francesco