MARK-AGE data management : Cleaning, exploration and visualization of data

Zitieren

Dateien zu dieser Ressource

Prüfsumme: MD5:b73bf44a4987175387f4aab8b55e1fee

BAUR, Jennifer, Maria MORENO-VILLANUEVA, Tobias KÖTTER, Thilo SINDLINGER, Alexander BÜRKLE, Michael R. BERTHOLD, Michael JUNK, 2015. MARK-AGE data management : Cleaning, exploration and visualization of data. In: Mechanisms of Ageing and Development. 151, pp. 38-44. ISSN 0047-6374. eISSN 1872-6216. Available under: doi: 10.1016/j.mad.2015.05.007

@article{Baur2015-11MARKA-31306, title={MARK-AGE data management : Cleaning, exploration and visualization of data}, year={2015}, doi={10.1016/j.mad.2015.05.007}, volume={151}, issn={0047-6374}, journal={Mechanisms of Ageing and Development}, pages={38--44}, author={Baur, Jennifer and Moreno-Villanueva, Maria and Kötter, Tobias and Sindlinger, Thilo and Bürkle, Alexander and Berthold, Michael R. and Junk, Michael} }

Bürkle, Alexander Kötter, Tobias Kötter, Tobias Sindlinger, Thilo 2015-06-29T09:22:56Z Junk, Michael Berthold, Michael R. Baur, Jennifer 2015-06-29T09:22:56Z MARK-AGE data management : Cleaning, exploration and visualization of data Moreno-Villanueva, Maria eng 2015-11 Junk, Michael Bürkle, Alexander Sindlinger, Thilo Baur, Jennifer Berthold, Michael R. Databases are an organized collection of data and necessary to investigate a wide spectrum of research questions. For data evaluation analyzers should be aware of possible data quality problems that can compromise results validity. Therefore data cleaning is an essential part of the data management process, which deals with the identification and correction of errors in order to improve data quality.<br />In our cross-sectional study, biomarkers of ageing, analytical, anthropometric and demographic data from about 3000 volunteers have been collected in the MARK-AGE database. Although several preventive strategies were applied before data entry, errors like miscoding, missing values, batch problems etc., could not be avoided completely. Such errors can result in misleading information and affect the validity of the performed data analysis.<br />Here we present an overview of the methods we applied for dealing with errors in the MARK-AGE database. We especially describe our strategies for the detection of missing values, outliers and batch effects and explain how they can be handled to improve data quality. Finally we report about the tools used for data exploration and data sharing between MARK-AGE collaborators. Moreno-Villanueva, Maria

Dateiabrufe seit 29.06.2015 (Informationen über die Zugriffsstatistik)

Baur_0-295717.pdf 19

Das Dokument erscheint in:

KOPS Suche


Stöbern

Mein Benutzerkonto