info:oai:generic.eprints.org:1776info:ofi/fmt:xml:xsd:oai_dc http://eprints.ncrm.ac.uk/1776/ Strategy for modelling non-random missing data mechanisms in observational studies using Bayesian methods Mason, Alexina Best, Nicky Richardson, Sylvia PLEWIS, IAN 3.6 Nonresponse 5.7 Longitudinal Data Analysis Observational studies are notoriously full of non-responses and missing values. Bayesian full probability modelling provides a °exible approach for analysing such data, allowing a plausible model to be built which can then be adapted to carry out a range of sensitivity analyses. In this context, we propose a strategy for using Bayesian methods for a `statistically principled' investigation of data which contains missing covariates and missing responses, likely to be non- random. The ¯rst part of this strategy entails constructing a `base model' by selecting a model of interest, then adding a sub-model to impute the missing covariates followed by a sub-model to allow informative missingness in the response. The second part involves running a series of sensitivity analyses to check the robustness of the conclusions. We implement our strategy to investigate some typical research questions relating to the prediction of income, using data from the Millennium Cohort Study. Imperial College London 2010 Working Paper NonPeerReviewed application/pdf en http://eprints.ncrm.ac.uk/1776/1/StrategySubmitted.pdf Mason, Alexina and Best, Nicky and Richardson, Sylvia and PLEWIS, IAN (2010) Strategy for modelling non-random missing data mechanisms in observational studies using Bayesian methods. Technical Report. Imperial College London. (Submitted)