Constraining TFractionFitter components to sum to 1

ROOT
1

I’m currently running TFractionFitter with 6 MC templates and noticed the fit fractions don’t sum to 1. The fit status is “SUCCESSFUL” and the error matrix is reported accurate. Here’s an example of one my my fit results:

par0 : 0.4912
par1 : 0.484464
par2 : 0.000684191
par3 : 0.000141439
par4 : 0.0231684
par5 : 0.000522719

Sum : 1.00018

Is this a bug? or is there a way I can manually force the sum to always be 1?

ROOT v6.20.04
Compiler: gcc9.3.0

2

So after some research it seems that this isn’t a bug but a consquence of how the maximum likelihood is found. Here’s a paper that discusses this and how to reweight the errors in cases where it’s needed.

1 Like
3

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