Poisson errors in histograms, EBinErrorOpt

ROOT
1

Hi all,

The error, as computed for TH1 histograms, when one uses the Sumw2() function as well is the “the error per bin is computed as the sqrt(sum of squares of weights)”.

I have background histograms with very few counts. I want to change it to Poisson errors per bin. I have seen a Public Types EBinErrorOpt{…} and a function called SetBinErrorOption(EBinErrorOpt type). However, whatever input I put into SetBinErrorOption doesn’t produce the correct results.

How do I implement this change?

2

Hi,

If the histogram is weighted, the error is not anymore Poisson and it is computed always as sqrt(sum of squares of weights)

Lorenzo

3

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.