Problems with errors in FIT

[s.elison]

Hello!
I was trying to do a linear fit but it isn’t working very well. When I try to fit it with errors my function’s parameters assumes values that don’t make sense!

With error in x values

Without error in x values

My code and data are attached.
data.txt (159 Bytes)
linear.cpp (1.5 KB)

The question is: Why when I set all errors for X values equals to 0.0005 it gives a bad fit?
Thanks!

[Wile_E_Coyote]

In ROOT, before you try to fit your graph or histogram, you MUST set “reasonable” initial values for ALL parameters of your function (except for some “built-in” formulas, like “gaus”, for which the standard fit procedure can automatically “guess” them), otherwise the fitting procedure may easily misbehave.

So, try something like: f->SetParameters(-3000., 300.);

See also the “initial pre-fit” + “final fit” trick in:

Fit of TGraphErrors fails, Fit of TGraph without Errors works

Two small fixes … tf_noerr->SetParameter(0, 2.5); // ... tf_err->SetParameter(0, 2.5); The real problem is that ROOT has often problems when fitting anything with “x errors” (and nobody cares, as usual). So, avoid setting “x errors”, if you can. If you cannot, I have found a “brutal fix” which often works, and in your case it would be … gr_err->Fit(tf_err, "WQRN"); // "initial pre-fit" gr_err->Fit(tf_err, "RM+"); // "final fit"

Fitting problem!

Your fit has the “STATUS=FAILED” (you could see it if you removed the “Q” fitting option). You need to set “reasonable” initial values of fit parameters so, try something like this: TF1 *gr_fit = ((TF1 *)(gROOT->GetFunction("pol1"))); gr_fit->SetParameters(-20, 2); gr->Fit(gr_fit, "Q"); Or you can try to “help” to make your fit more “foolproof”: TF1 *gr_fit = ((TF1 *)(gROOT->GetFunction("pol1"))); gr->Fit(gr_fit, "WQ"); // "initial pre-fit" gr->Fit(gr_fit, "Q"); // "final fit"

[s.elison]

It worked! Thanks!