MULTIPLE IMPUTATION AS A MISSING DATA MACHINE

Authors
BRAND J VANBUUREN S VANMULLIGEN EM TIMMERS T GELSEMA E
Citation
J. Brand et al., MULTIPLE IMPUTATION AS A MISSING DATA MACHINE, Journal of the American Medical Informatics Association, 1994, pp. 303-306
Citations number
6
Categorie Soggetti
Information Science & Library Science","Medicine Miscellaneus","Computer Science Information Systems
Journal title
Journal of the American Medical Informatics Association → ACNP
ISSN journal
10675027
Year of publication
1994
Supplement
S
Pages
303 - 306
Database
ISI
SICI code
1067-5027(1994):<303:MIAAMD>2.0.ZU;2-5
Abstract
This paper deals with problems concerning missing data in clinical dat abases. After signalling some shortcomings of popular solutions to inc omplete data problems, we outline the concepts behind multiple imputat ion. Multiple imputation is a statistically sound method for handling incomplete data. Application of multiple imputation requires a lot of work and not every user is able to do this. A transparent implementati on of multiple imputation is necessary. Such an implementation is poss ible in the HERMES medical workstation. A remaining problem is to find proper imputations.