this is for holding javascript data
Graham McVicker edited Estimating overdispersion parameters.tex
over 9 years ago
Commit id: cace41af173e9a557c93883034d15513bdee3aff
deletions | additions
diff --git a/Estimating overdispersion parameters.tex b/Estimating overdispersion parameters.tex
index 77926f0..2660697 100644
--- a/Estimating overdispersion parameters.tex
+++ b/Estimating overdispersion parameters.tex
...
\subsection{Estimating overdispersion parameters}
In order to estimate the genome-wide overdispersion parameters $\Phi_i$ and $\Upsilon_i$, we use the same likelihood equations as in the CHT, but assume that there are no genetic effects. This means that for the read depth part of the test the mean estimate,
$\lambda$, $\lambda_{hi}$, is equal to the expected counts,
$T^*_{ij}$. For $T^*_{ij}$, and for the
allele specific allele-specific part of the test,
$p$ $p_h$ is equal to $0.5$.
The fraction of reads comSince Since the allele specific and read depth parts of the likelihood equation are independent, we can fit the overdispersion parameters separately.
\subsubsection{Beta-Negative-Binomial}
In order to To find the maximum likelihood estimate of $\Phi_i$ we need to sum the likelihood
equation across all regions. This presents a problem, as $\eta_j$ must also be estimated for each region. We therefore interatively estimate $\eta_j$ using the equation
\[
\textrm{L}\left(\eta_j %\[
%\textrm{L}\left(\eta_j \left| D \right. \right) = \prod_i \left[ \Pr_{\mathrm{BNB}} \left( X = x_{ij}
\left| %\left| \lambda = T^*_{ij}, \Phi_i, \eta_j \right. \right) \right]
\] %\]
and then $\Phi_i using the equation
\[
\textrm{L}\left(\Phi_i %\[
%\textrm{L}\left(\Phi_i \left| D \right. \right) = \prod_j \left[ \Pr_{\mathrm{BNB}} \left( X = x_{ij}
\left| %\left| \lambda = T^*_{ij}, \Phi_i, \eta_j \right. \right) \right]
\] %\]
\subsubsection{Beta-Binomial}
\subsubsection{Beta-Binomial}