Linked Life Data

16998821

Source:http://linkedlifedata.com/resource/pubmed/id/16998821

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
11
pubmed:dateCreated
2007-4-11
pubmed:abstractText
We consider Bayesian sensitivity analysis for unmeasured confounding in observational studies where the association between a binary exposure, binary response, measured confounders and a single binary unmeasured confounder can be formulated using logistic regression models. A model for unmeasured confounding is presented along with a family of prior distributions that model beliefs about a possible unknown unmeasured confounder. Simulation from the posterior distribution is accomplished using Markov chain Monte Carlo. Because the model for unmeasured confounding is not identifiable, standard large-sample theory for Bayesian analysis is not applicable. Consequently, the impact of different choices of prior distributions on the coverage probability of credible intervals is unknown. Using simulations, we investigate the coverage probability when averaged with respect to various distributions over the parameter space. The results indicate that credible intervals will have approximately nominal coverage probability, on average, when the prior distribution used for sensitivity analysis approximates the sampling distribution of model parameters in a hypothetical sequence of observational studies. We motivate the method in a study of the effectiveness of beta blocker therapy for treatment of heart failure.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:chemical
pubmed:status
MEDLINE
pubmed:month
May
pubmed:issn
0277-6715
pubmed:author
pubmed:copyrightInfo
Copyright 2006 John Wiley & Sons, Ltd.
pubmed:issnType
Print
pubmed:day
20
pubmed:volume
26
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
2331-47
pubmed:meshHeading
pubmed:year
2007
pubmed:articleTitle
Bayesian sensitivity analysis for unmeasured confounding in observational studies.
pubmed:affiliation
Department of Statistics, University of British Columbia, Vancouver BC, Canada. lawrence@stat.ubc.ca
pubmed:publicationType
Journal Article, Research Support, Non-U.S. Gov't