• English
    • suomi
  • English 
    • English
    • suomi
  • Login
View Item 
  •   Home
  • Artikkelit
  • Terveystieteiden tiedekunta
  • View Item
  •   Home
  • Artikkelit
  • Terveystieteiden tiedekunta
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Improving data sharing in research with context-free encoded missing data

Thumbnail
View/Open
Article (293.1Kb)
Self archived version
published version
Date
2017
Author
Hoevenaar-Blom MP
Guillemont J
Ngandu T
Beishuizen CRL
Coley N
Moll van Charante EP
Andrieu S
Kivipelto M
Soininen H
Brayne C
Meiller Y
Richard E
Unique identifier
10.1371/journal.pone.0182362
Metadata
Show full item record
More information
Research Database SoleCris

Self-archived article

Citation
Hoevenaar-Blom MP. Guillemont J. Ngandu T. Beishuizen CRL. Coley N. Moll van Charante EP. Andrieu S. Kivipelto M. Soininen H. Brayne C. Meiller Y. Richard E. (2017). Improving data sharing in research with context-free encoded missing data.  PLOS ONE, 12 (9) , e0182362. 10.1371/journal.pone.0182362.
Rights
© Hoevenaar-Blom et al.
Licensed under
CC BY http://creativecommons.org/licenses/by/4.0/
Abstract

Lack of attention to missing data in research may result in biased results, loss of power and reduced generalizability. Registering reasons for missing values at the time of data collection, or—in the case of sharing existing data—before making data available to other teams, can save time and efforts, improve scientific value and help to prevent erroneous assumptions and biased results. To ensure that encoding of missing data is sufficient to understand the reason why data are missing, it should ideally be context-free. Therefore, 11 context-free codes of missing data were carefully designed based on three completed randomized controlled clinical trials and tested in a new randomized controlled clinical trial by an international team consisting of clinical researchers and epidemiologists with extended experience in designing and conducting trials and an Information System expert. These codes can be divided into missing due to participant and/or participation characteristics (n = 6), missing by design (n = 4), and due to a procedural error (n = 1). Broad implementation of context-free missing data encoding may enhance the possibilities of data sharing and pooling, thus allowing more powerful analyses using existing data

URI
https://erepo.uef.fi/handle/123456789/4284
Link to the original item
http://dx.doi.org/10.1371/journal.pone.0182362
Collections
  • Terveystieteiden tiedekunta
University of Eastern Finland
OpenAccess
eRepo
erepo@uef.fi
Send Feedback
OpenUEF
Service provided by
the University of Eastern Finland Library
Library web pages
Twitter
Facebook
Youtube
Library blog
 

Browse

All of the ArchiveResource types & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login
University of Eastern Finland
OpenAccess
eRepo
erepo@uef.fi
Send Feedback
OpenUEF
Service provided by
the University of Eastern Finland Library
Library web pages
Twitter
Facebook
Youtube
Library blog