Graphical models for inference under outcome-dependent sampling

V Didelez, S Kreiner, N Keiding

Research output: Contribution to journalArticle (Academic Journal)peer-review

32 Citations (Scopus)

Abstract

We consider situations where data have been collected such that the sampling depends on the outcome of interest and possibly further covariates, as for instance in case-control studies. Graphical models represent assumptions about the conditional independencies among the variables. By including a node for the sampling indicator, assumptions about sampling processes can be made explicit. We demonstrate how to read off such graphs whether consistent estimation of the association between exposure and outcome is possible. Moreover, we give sufficient graphical conditions for testing and estimating the causal effect of exposure on outcome. The practical use is illustrated with a number of examples.
Translated title of the contributionGraphical models for inference under outcome dependent sampling
Original languageEnglish
Pages (from-to)368 - 387
Number of pages20
JournalStatistical Science
Volume25
Issue number3
DOIs
Publication statusPublished - Aug 2010

Fingerprint Dive into the research topics of 'Graphical models for inference under outcome-dependent sampling'. Together they form a unique fingerprint.

Cite this