Re: How to catch Fit results manually

Hi Asif,

I believe error extraction is a function (a.k.a. method) of the TF1 rather than the TFormula it inherits from. A TFormula does not have errors, but only parameters, so errors are only available from something (a TF1) that can be fit.

Ain't Object Oreintation grand? Anyway the header files should give you everything you need, even if you have to go climbing up and down the tree to find 'em.

-Art

A.E. Snyder, The Former Group C (TFC)        \!c*p?/
SLAC Mail Stop #95                          ((.   .))
Box 4349                                        |
Stanford, Ca, USA, 94309                      '\|/`
e-mail:snyder_at_slac.stanford.edu                 o
phone:650-926-2701                              _
http://www.slac.stanford.edu/~snyder          BaBar
FAX:707-313-0250                          Collaboration
                                                 &
                                            Fermi/GLAST

On Wed, 29 Feb 2012, Asif Saddique wrote:

> Thanks Arthur!
> I got your point. So, parameter 1 is the Mean Value and parameter 2 is the
> Sigma but still i don't understand how to get errors on these. Can you
> please point out something about errors?
>
> Cheers, Asif
>
>
>
>
> On Wed, Feb 29, 2012 at 5:24 PM, Arthur E. Snyder <snyder_at_slac.stanford.edu>
> wrote:
> Assuming your fitting a TF1 to a histogram see
>
> http://root.cern.ch/root/html/TF1.html
>
> and (for inherited functions)
>
> http://root.cern.ch/root/html/TFormula.html
>
> -Art S
>
> A.E. Snyder, The Former Group C (TFC)        \!c*p?/
> SLAC Mail Stop #95                          ((.   .))
> Box 4349                                        |
> Stanford, Ca, USA, 94309                      '\|/`
> e-mail:snyder_at_slac.stanford.edu                 o
> phone:650-926-2701                              _
> http://www.slac.stanford.edu/~snyder          BaBar
> FAX:707-313-0250                          Collaboration
>                                                &
>                                           Fermi/GLAST
>
>
>
>
> On Wed, 29 Feb 2012, Asif Saddique wrote:
>
> Hi rooters,
>
> I am fitting a Gaussian on TH1D and I see following values
> of Mean & Sigma
> in my terminal:
> ===========================================================
>  FCN=86.9094 FROM MIGRAD    STATUS=CONVERGED      63
> CALLS          64 TOTAL
>                      EDM=2.49833e-09    STRATEGY= 1     
> ERROR MATRIX
> ACCURATE
>   EXT PARAMETER                                  
> STEP         FIRST  
>   NO.   NAME      VALUE            ERROR         
> SIZE      DERIVATIVE
>    1  Constant     5.98744e+03   4.61314e+01  
> 1.65706e-01  -1.72560e-06
>    2  Mean         9.20998e+01   1.10379e-01  
> 5.04750e-04  -4.60640e-05
>    3  Sigma        1.82326e+01   8.71316e-02  
> 5.68693e-06  -5.16419e-02
> ============================================================
>
> I can see Mean & Sigma from here but how can get them
> manually. Actually, i
> want to print them in the title of my Histogram. I will
> convert the value
> into TString then i will put it in the title but how I can
> get these values,
> I mean
>
>
> cout<<"Mean Value=  "<<????<<<" with Error 
> ="<<????<<endl;
> cout<<"Sigma Value=  "<<????<<"  with Error 
> ="<<????<<endl;
>
> should output following:
>
> Mean Value= 9.20998e+01  with Error  =4.61314e+01
> Sigma Value= 1.82326e+01  with Error =8.71316e-02
>
> But how ?
>
> Thanks for help.
>
> Cheers, Asif
>
>
>
>
>
>
>
Received on Thu Mar 01 2012 - 02:33:01 CET