Sökning: onr:"swepub:oai:prod.swepub.kib.ki.se:145907924" >
A note on a sensiti...
-
Sjolander, AKarolinska Institutet
(författare)
A note on a sensitivity analysis for unmeasured confounding, and the related E-value
- Artikel/kapitelEngelska2020
Förlag, utgivningsår, omfång ...
-
2020-12-31
-
Walter de Gruyter GmbH,2020
Nummerbeteckningar
-
LIBRIS-ID:oai:prod.swepub.kib.ki.se:145907924
-
http://kipublications.ki.se/Default.aspx?queryparsed=id:145907924URI
-
https://doi.org/10.1515/jci-2020-0012DOI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:vet swepub-contenttype
-
Ämneskategori:art swepub-publicationtype
Anmärkningar
-
Unmeasured confounding is one of the most important threats to the validity of observational studies. In this paper we scrutinize a recently proposed sensitivity analysis for unmeasured confounding. The analysis requires specification of two parameters, loosely defined as the maximal strength of association that an unmeasured confounder may have with the exposure and with the outcome, respectively. The E-value is defined as the strength of association that the confounder must have with the exposure and the outcome, to fully explain away an observed exposure-outcome association. We derive the feasible region of the sensitivity analysis parameters, and we show that the bounds produced by the sensitivity analysis are not always sharp. We finally establish a region in which the bounds are guaranteed to be sharp, and we discuss the implications of this sharp region for the interpretation of the E-value. We illustrate the theory with a real data example and a simulation.
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Karolinska Institutet
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:JOURNAL OF CAUSAL INFERENCE: Walter de Gruyter GmbH8:1, s. 229-2482193-36772193-3685
Internetlänk
Hitta via bibliotek
Till lärosätets databas