Invited Commentary: Selection Bias Without Colliders

Abstract In causal analyses, conditioning on a collider generally results in selection bias. Conditioning on a prognostic factor that is independent of the exposure—and therefore is not a collider—can also result in selection bias when 1) the exposure has a non-null effect on the outcome and 2) the...

Full description

Bibliographic Details
Published in:American Journal of Epidemiology
Main Author: Hernán, Miguel A.
Other Authors: National Institutes of Health
Format: Article in Journal/Newspaper
Language:English
Published: Oxford University Press (OUP) 2017
Subjects:
Greenland
Online Access:http://dx.doi.org/10.1093/aje/kwx077
http://academic.oup.com/aje/article-pdf/185/11/1048/29016569/kwx077.pdf
id croxfordunivpr:10.1093/aje/kwx077
record_format openpolar
spelling croxfordunivpr:10.1093/aje/kwx077 2024-06-23T07:53:17+00:00 Invited Commentary: Selection Bias Without Colliders Hernán, Miguel A. National Institutes of Health 2017 http://dx.doi.org/10.1093/aje/kwx077 http://academic.oup.com/aje/article-pdf/185/11/1048/29016569/kwx077.pdf en eng Oxford University Press (OUP) American Journal of Epidemiology volume 185, issue 11, page 1048-1050 ISSN 0002-9262 1476-6256 journal-article 2017 croxfordunivpr https://doi.org/10.1093/aje/kwx077 2024-06-11T04:16:32Z Abstract In causal analyses, conditioning on a collider generally results in selection bias. Conditioning on a prognostic factor that is independent of the exposure—and therefore is not a collider—can also result in selection bias when 1) the exposure has a non-null effect on the outcome and 2) the association between the noncollider and the outcome is heterogenous across levels of the exposure. This result was empirically demonstrated by Greenland in 1977 (Am J Epidemiol. 1977;106(3):184–187). Article in Journal/Newspaper Greenland Oxford University Press Greenland American Journal of Epidemiology 185 11 1048 1050
institution Open Polar
collection Oxford University Press
op_collection_id croxfordunivpr
language English
description Abstract In causal analyses, conditioning on a collider generally results in selection bias. Conditioning on a prognostic factor that is independent of the exposure—and therefore is not a collider—can also result in selection bias when 1) the exposure has a non-null effect on the outcome and 2) the association between the noncollider and the outcome is heterogenous across levels of the exposure. This result was empirically demonstrated by Greenland in 1977 (Am J Epidemiol. 1977;106(3):184–187).
author2 National Institutes of Health
format Article in Journal/Newspaper
author Hernán, Miguel A.
spellingShingle Hernán, Miguel A.
Invited Commentary: Selection Bias Without Colliders
author_facet Hernán, Miguel A.
author_sort Hernán, Miguel A.
title Invited Commentary: Selection Bias Without Colliders
title_short Invited Commentary: Selection Bias Without Colliders
title_full Invited Commentary: Selection Bias Without Colliders
title_fullStr Invited Commentary: Selection Bias Without Colliders
title_full_unstemmed Invited Commentary: Selection Bias Without Colliders
title_sort invited commentary: selection bias without colliders
publisher Oxford University Press (OUP)
publishDate 2017
url http://dx.doi.org/10.1093/aje/kwx077
http://academic.oup.com/aje/article-pdf/185/11/1048/29016569/kwx077.pdf
geographic Greenland
geographic_facet Greenland
genre Greenland
genre_facet Greenland
op_source American Journal of Epidemiology
volume 185, issue 11, page 1048-1050
ISSN 0002-9262 1476-6256
op_doi https://doi.org/10.1093/aje/kwx077
container_title American Journal of Epidemiology
container_volume 185
container_issue 11
container_start_page 1048
op_container_end_page 1050
_version_ 1802644858096058368

Similar Items