Show simple item record

dc.contributor.authorSperrin, Matthew; orcid: 0000-0002-5351-9960; email: matthew.sperrin@manchester.ac.uk
dc.contributor.authorMartin, Glen P.
dc.date.accessioned2021-07-08T15:32:14Z
dc.date.available2021-07-08T15:32:14Z
dc.date.issued2020-07-08
dc.date.submitted2019-11-18
dc.identifierhttps://chesterrep.openrepository.com/bitstream/handle/10034/625184/additional-files.zip?sequence=2
dc.identifierhttps://chesterrep.openrepository.com/bitstream/handle/10034/625184/12874_2020_Article_1068_nlm.xml?sequence=3
dc.identifierhttps://chesterrep.openrepository.com/bitstream/handle/10034/625184/12874_2020_Article_1068.pdf?sequence=4
dc.identifier.citationBMC Medical Research Methodology, volume 20, issue 1, page 185
dc.identifier.urihttp://hdl.handle.net/10034/625184
dc.descriptionFrom Springer Nature via Jisc Publications Router
dc.descriptionHistory: received 2019-11-18, accepted 2020-06-28, registration 2020-06-29, pub-electronic 2020-07-08, online 2020-07-08, collection 2020-12
dc.descriptionPublication status: Published
dc.descriptionFunder: Medical Research Council; doi: http://dx.doi.org/10.13039/501100000265; Grant(s): MR/T025085/1
dc.description.abstractAbstract: Background: Within routinely collected health data, missing data for an individual might provide useful information in itself. This occurs, for example, in the case of electronic health records, where the presence or absence of data is informative. While the naive use of missing indicators to try to exploit such information can introduce bias, its use in conjunction with multiple imputation may unlock the potential value of missingness to reduce bias in causal effect estimation, particularly in missing not at random scenarios and where missingness might be associated with unmeasured confounders. Methods: We conducted a simulation study to determine when the use of a missing indicator, combined with multiple imputation, would reduce bias for causal effect estimation, under a range of scenarios including unmeasured variables, missing not at random, and missing at random mechanisms. We use directed acyclic graphs and structural models to elucidate a variety of causal structures of interest. We handled missing data using complete case analysis, and multiple imputation with and without missing indicator terms. Results: We find that multiple imputation combined with a missing indicator gives minimal bias for causal effect estimation in most scenarios. In particular the approach: 1) does not introduce bias in missing (completely) at random scenarios; 2) reduces bias in missing not at random scenarios where the missing mechanism depends on the missing variable itself; and 3) may reduce or increase bias when unmeasured confounding is present. Conclusion: In the presence of missing data, careful use of missing indicators, combined with multiple imputation, can improve causal effect estimation when missingness is informative, and is not detrimental when missingness is at random.
dc.languageen
dc.publisherBioMed Central
dc.rightsLicence for this article: http://creativecommons.org/licenses/by/4.0/
dc.sourceeissn: 1471-2288
dc.subjectResearch Article
dc.subjectData analysis, statistics and modelling
dc.subjectMissing data
dc.subjectMissing indicator
dc.subjectMultiple imputation
dc.subjectSimulation study
dc.titleMultiple imputation with missing indicators as proxies for unmeasured variables: simulation study
dc.typearticle
dc.date.updated2021-07-08T15:32:14Z
dc.date.accepted2020-06-28


Files in this item

Thumbnail
Name:
additional-files.zip
Size:
164.0Kb
Format:
Unknown
Thumbnail
Name:
12874_2020_Article_1068_nlm.xml
Size:
124.8Kb
Format:
XML
Thumbnail
Name:
12874_2020_Article_1068.pdf
Size:
2.327Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record