this is for holding javascript data
Patrick Janot edited Statistical analysis.tex
about 9 years ago
Commit id: e605876c547878d57402df05c17e620f18b258a5
deletions | additions
diff --git a/Statistical analysis.tex b/Statistical analysis.tex
index e614671..3dc0f41 100644
--- a/Statistical analysis.tex
+++ b/Statistical analysis.tex
...
where $N$ is the total number of ${\rm t \bar t}$ events observed in the data sample, $\mu$ is the number of events expected for the integrated luminosity ${\cal L}$ of the data sample ($\mu = \sigma_{\rm tot} \times {\cal L}$), and
\begin{equation}
p(k) = {1 \over \sigma_{\rm tot} } { {\rm d}^2\sigma \over {\rm d}x {\rm d}\cos\theta } {\rm , with \ }
\sigma_{\rm tot} = \int
{\rm d}x {\rm d}\cos\theta { {\rm d}^2\sigma \over {\rm d}x {\rm d}\cos\theta }
{\rm d}x {\rm d}\cos\theta .
\end{equation}
The covariance matrix obtained from the numerical minimization of the negative log-likelihood is then inverted to get the uncertainties on the form factors, $\sigma(\delta_i)$. It can be shown~\cite{Davier_1993} that, in the linear form given in Eq.~\ref{eq:optimal}, this method leads to optimal statistical uncertainties on the form factors. The functions $f_i(x,\cos\theta)$ are therefore called "optimal observables". It turns out~\cite{Diehl_1994} that the covariance matrix, hence the statistical uncertainties on the form factors, can be obtained analytically in the limit of large number of events, which is the case considered in this letter. If the total event rate is included in the derivation of the likelihood, as is the case in Eq.~\ref{eq:likelihood}, the elements of the covariance matrix $V$ are giveb by
\begin{equation}
V_{ij} = {\cal L} \int
{\rm d}x {\rm d}\cos\theta { f_i(x,\cos\theta) \times f_j(x,\cos\theta) \over S^0(x,\cos\theta)}
{\rm d}x {\rm d}\cos\theta
\end{equation}