Original title:
Imputation Of Missing Values In Clinical Data
Translated title:
Imputation of missing values in clinical data
Authors:
BIRKLBAUER, Micha Johannes Document type: Bachelor's theses
Year:
2019
Language:
cze Abstract:
Imputation of missing data is a crucial step in data analysis since many statistical methods require complete datasets. In that regard MissForest imputation is a powerful tool that seems to outperform most other imputation approaches. This analysis evaluates how good imputation using MissForest is compared to other methods like imputation by Multivariate Imputation by Chained Equations (MICE), Restricted Boltzmann Machines (RBM) or the standard strawman (mean) imputation in a clinical dataset that is used to predict the mortality of patients after heart valve surgery.
Keywords:
clinical data; imputation; machine learning; mice; missforest; missing data; multivariate imputation by chained equations; rbm; restricted boltzmann machine; clinical data; imputation; machine learning; mice; missforest; missing data; multivariate imputation by chained equations; rbm; restricted boltzmann machine Citation: BIRKLBAUER, Micha Johannes. Imputation Of Missing Values In Clinical Data. České Budějovice, 2019. bakalářská práce (Bc.). JIHOČESKÁ UNIVERZITA V ČESKÝCH BUDĚJOVICÍCH. Přírodovědecká fakulta
Institution: University of South Bohemia in České Budějovice
(web)
Document availability information: Fulltext is available in the Digital Repository of University of South Bohemia. Original record: http://www.jcu.cz/vskp/55039