Re: [ROOT] Multi dimensional fit for the data.

From: Rene Brun (Rene.Brun@cern.ch)
Date: Tue Nov 25 2003 - 21:16:29 MET


Hi,

See class TMultiDimFit
http://root.cern.ch/root/htmldoc/TMultiDimFit.html

and an example with the tutorial
$ROOTSYS/tutorials/multidimfit.C

Rene Brun

On Tue, 25 Nov 2003, 
Venkatesh Kaushik wrote:

> 
> Hi ROOTers,
> I have a set of data which is fairly gaussian
> i have to fit a function that looks like this
> 
> U[i] = A* X1[i] + B * X2[i] + C * X3[i] + D * X4[i] , i =1, N
> 
> U --> dependent variable ( and also input data)
> X1 thro X4 --> Independent variables, not correlated, (also the the input data)
> N --> Number of data points
> i --> Index that runs from 1 thro N
> 
> 
> If i just plot X1, X2, X3 and X4, and U, i get a
> gaussian distribution for each.
> 
> My questions are
> 1) is this a candidate for a multidimensional fit?
> 2) if so, i have to find the co-efficients A, B, C and D that best
>    represent the data.
> 
> Can you please help me?
> Thanks in advance.
> 
> Venkat.
> 



This archive was generated by hypermail 2b29 : Thu Jan 01 2004 - 17:50:17 MET