binned_maximum_likelihood¶
-
minkit.
binned_maximum_likelihood
(pdf, data)[source]¶ Definition of the binned maximum likelihood FCN. The output is two times the logarithm of the likelihood, and is computed as
\[\text{FCN} = -2 \times \left[\sum_{b=0}^M n_b \log\frac{n_b}{f(b;\vec{\theta})} + f(b;\vec{\theta}) - n_b\right],\]where \(n_b\) is the number of entries in bin b, \(f(b;\vec{\theta})\) is the integral of the function to minimize in the bin b (without normalization), \(\vec{\theta}\) are the function parameters.
- Parameters
pdf (PDF) – function to evaluate.
data (BinnedDataSet) – data to evaluate.
- Returns
value of the FCN.
- Return type