[Ifeffit] ???

Matt Newville newville at cars.uchicago.edu
Sun May 1 15:21:20 CDT 2005

Hi Elena,

> >From where to get the error bars for number of neighbours,
> >distance and sigsqr (ss)?

I'm not sure whether you are asking where the error bars are
reported or how they are determined.  They should be reported in
the Fit Summary window that pops up after the fit.  The
calculation is a bit more involved, and is described in the 
Feffit manual.

> What are Chi-square,Reduced Chi-square and R-factor and how
> should be their values in a fit?

Does this help?

If not, maybe I'm not understanding the question.
> Sometimes it happen that "R-factor for this data set" does not
> have the same value as the first R-factor from results. Why?

For a fit with more than one data set, the fit to one data set 
might be better than the fit to another data set.  In that case 
the partial R-factors would be different.

If that's not enough, please ask again.


More information about the Ifeffit mailing list