Hi Rene,
Fine with me; it was just a suggestion.
Anyhow, TMath would indeed be abetter place to have this
facility. However, once the TMath stuff is implemented I would
suggest to interface a new TH1::GetCentralMoment to it so that
all this is also available from histos and the calculations
are performed in 1 central place (easier to fix bugs ;)
Cheers,
Nick.
> Hi Nick,
>
> We may consider adding a TMath::CentralMoment function,
> but we will keep TH1 as it is now with the 4 functions
> GetMean,GetRMS,GetSkewness and GetKurtosis.
>
> Rene Brun
>
> On Tue, 26 Apr
> 2005, Nick van Eijndhoven wrote:
>
> > Hi Rene,
> > What about introducing a more general faility
> > GetCentralMoment(n) to return the n-th central moment ?
> > In such a way one directly covers the mean, variance,
> > skewness, kurtosis etc....
> >
> > Cheers,
> > Nick.
> >
> > ----- Original Message -----
> > From: "Rene Brun" <brun_at_pcroot.cern.ch>
> > To: "Damir Buskulic" <buskulic_at_lapp.in2p3.fr>
> > Cc: <Anna.Krechtchouk_at_cern.ch>; <roottalk_at_pcroot.cern.ch>
> > Sent: Tuesday, April 26, 2005 3:19 PM
> > Subject: Re: [ROOT] skewness or kurtosis ?
> >
> >
> > > Hi Damir,
> > >
> > > Thanks to Anna Kreshuk for implementing your requested functions.
> > > They are now in CVS head. see:
> > > http://root.cern.ch/root/htmldoc/TH1.html#TH1:GetSkewness
> > > http://root.cern.ch/root/htmldoc/TH1.html#TH1:GetKurtosis
> > >
> > > Rene Brun
> > >
> > > On Mon,
> > > 25 Apr 2005, Damir Buskulic wrote:
> > >
> > > > Hi,
> > > >
> > > > Is there a method in TH1 (for instance) that calculates the skewness
> > > > and/or kurtosis of a given distribution ?
> > > >
> > > > Cheers
> > > >
> > > > Damir
> > > >
> > > > ====================================
> > > > Damir Buskulic, Universite de Savoie/LAPP
> > > > Chemin de Bellevue, B.P. 110, F-74941 Annecy-le-Vieux Cedex, FRANCE
> > > > Tel : +33 (0)450091600
> > > > e-mail: buskulic_at_lapp.in2p3.fr
> > > > ====================================
> > > >
> > >
> >
>
Received on Wed Apr 27 2005 - 10:19:36 MEST
This archive was generated by hypermail 2.2.0 : Tue Jan 02 2007 - 14:45:07 MET