this is for holding javascript data
Alex Rubinsteyn edited section_Comparison_of_imputation_algorithms__.tex
almost 8 years ago
Commit id: d99b5a6b370388a69dbe6e37c887b6854aaea43f
deletions | additions
diff --git a/section_Comparison_of_imputation_algorithms__.tex b/section_Comparison_of_imputation_algorithms__.tex
index b603ab0..dca6263 100644
--- a/section_Comparison_of_imputation_algorithms__.tex
+++ b/section_Comparison_of_imputation_algorithms__.tex
...
\item {\bf MICE}~\cite{Azur_2011}: Average multiple imputations generated using Gibbs sampling from the joint distribution of columns.
\end{itemize}
We evaluated the performance of these methods using three-fold cross validation on BD2009 (~\ref{tab:imputation}), only considering peptides which occurred in at least three alleles and excluding alleles with less than five measurements.
All imputation methods were implemented in the \textit{fancyimpute} Python library~\cite{fancyimpute-0-0-16}. Since MICE outperformed the other methods on two of the three predictor metrics, we selected it for the subsequent neural network experiments.
\begin{table}[htbp]
\centering