Re: [ROOT] error matrix

• Next message: Kay Ulbrich: "[ROOT] Superimposing Histograms with different line styles"
• Previous message: Matt Fritts: "[ROOT] error matrix"
• In reply to: Matt Fritts: "[ROOT] error matrix"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Hi Matt,

See my reply to the same question at

http://root.cern.ch/root/roottalk/roottalk02/2279.html

Rene Brun

On Wed, 5 Jun 2002, Matt Fritts wrote:

> I have been fitting TH1 spectral data to a user-defined function. In the 
> past I have used the parameter errors for the fit values. For current 
> work I find that I need to know the correlation of the errors of 
> different paramaters. I understand that for this I must know the values 
> of different terms in the error matrix.
> 
> How do I extract values from the error matrix after using "fit" for a 
> TH1? I see in the reference guide that TMinuit has a member "mnemat"... 
> but I am not using TMinuit directly.
> 
> Thanks in advance for your help!
> 
> Matt Fritts
> University of Toledo
> 

• Next message: Kay Ulbrich: "[ROOT] Superimposing Histograms with different line styles"
• Previous message: Matt Fritts: "[ROOT] error matrix"
• In reply to: Matt Fritts: "[ROOT] error matrix"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Sat Jan 04 2003 - 23:50:55 MET