Fit: investigate log-likelihood, Poisson statistics
|Status:||Backlog||Start date:||19 Jan 2017|
Request from Sebastian:
* Given the low number of neutrons, I think it might be important to use Poisson statistics when fitting. Not sure if you do.
In ROOT, from where we have borrowed fitting engine, there is a possibility to select Log-Likelihood for histograms with counts (and low statistics).