Premium
Missing data in trial‐based cost‐effectiveness analysis: the current state of play
Author(s) -
Noble Sian Marie,
Hollingworth William,
Tilling Kate
Publication year - 2012
Publication title -
health economics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.55
H-Index - 109
eISSN - 1099-1050
pISSN - 1057-9230
DOI - 10.1002/hec.1693
Subject(s) - missing data , randomized controlled trial , transparency (behavior) , computer science , cost effectiveness , data mining , medicine , risk analysis (engineering) , machine learning , surgery , computer security
SUMMARY Randomised controlled trial (RCT)‐based cost‐effectiveness analyses, which are prone to missing data, are increasingly used in healthcare technology assessment. This has highlighted the need for appropriate methodological approaches to the handling of missing data. This paper reviews missing data methodology used in RCT‐based cost‐effectiveness analyses since 2003. Complete case analysis, which may lead to inappropriate conclusions, is still the most popular approach and its use has increased with time. The degree of missing data in cost‐effectiveness analyses was often poorly reported and the methodology was often unclear. Reporting of missing data sensitivity analyses would improve article transparency. Copyright © 2010 John Wiley & Sons, Ltd.