Hi!

I am trying to find a simple way to maximize a likelihood like this one:

L = Poisson(N, ),

where N is a number, - depends on a parameter. I do not have any events, this is it: I need to find the value of the parameter that maximizes the likelihood.

Could anyone suggest a way to implement this? I tried to do this with RooFit by making the likelihood into a PDF, N - an observable, and fit it to a dataset with only one event that contains N. This doesn’t work however because RooFit tries to normalize the PDF, which creates an extra free parameter.

I believe that there is a way to prevent RooFit from normalizing the PDF. That would do the trick, wouldn’t it? I couldn’t find how though…

Perhaps, there is a much simpler way to do this maximization. Any suggestion would be welcome!