BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
LAST-MODIFIED:20070321T162204
SEQUENCE:0
CONTACT:m.cortina@ich.ucl.ac.uk
ORGANIZER:Institute of Child Health Department of Paediatric Epidemiology a
 nd Biostatistics
DTEND:20070523T150000
UID:2008-09-07T18:43:42-0400_94230355@socialweb1
DESCRIPTION:Multiple Imputation (MI) is now well established as a flexible\
 , general\, method for the analysis of data sets with missing values. Most 
 implementations assume the missing data are 'Missing At Random' (MAR)\, i.e
 . given the observed data\, the reason for the missing data does not depend
  on the unseen data.\n\nHowever\, although this is a helpful and simplifyin
 g  working assumption\, it is unlikely to be true in practice. Assessing th
 e sensitivity of the analysis to the MAR assumption is therefore important.
  However\, there is very limited MI software for this. Further\, analysis o
 f a data set with missing values that are Not Missing At Random (NMAR) is c
 omplicated by the need to extend the MAR imputation model to include a mode
 l for the reason for dropout.\n\nHere\, we propose a simple alternative. We
  first impute under MAR and obtain parameter estimates for each imputed dat
 a set. The overall NMAR parameter estimate is a weighted average of these p
 arameter estimates\, where the weights depend on the assumed degree of depa
 rture from MAR. In some settings\, this approach gives results that closely
  agree with joint modelling as the number of imputations increases. In othe
 rs\, it provides ball-park estimates of the results of full NMAR modelling\
 , indicating the extent to which it is necessary and providing a check on i
 ts results. We illustrate our approach with a small simulation study\, and 
 the analysis of data from a trial of interventions to improve the quality o
 f peer review.
SUMMARY:Sensitivity analysis after multiple imputation under missing at ran
 dom - a weighting approach
DTSTART:20070523T140000
CREATED:20070321T162204
DTSTAMP:20080907T184342
LOCATION:Institute of Child Health Wellcome Trust Building Leolin Price The
 atre
END:VEVENT
END:VCALENDAR