2011
DOI: 10.1093/biomet/asr059
|View full text |Cite
|
Sign up to set email alerts
|

Directed acyclic graphs with edge-specific bounds

Abstract: SUMMARYWe give a definition of a bounded edge within the causal directed acyclic graph framework. A bounded edge generalizes the notion of a signed edge and is defined in terms of bounds on a ratio of survivor probabilities. We derive rules concerning the propagation of bounds. Bounds on causal effects in the presence of unmeasured confounding are also derived using bounds related to specific edges on a graph. We illustrate the theory developed by an example concerning estimating the effect of antihistamine tr… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2014
2014
2022
2022

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(2 citation statements)
references
References 16 publications
0
2
0
Order By: Relevance
“…In a signed DAG, edges are marked with the direction (positive or negative) of the average effect for each pair of directly connected variables, conditional on other relevant variables. The use of signed DAGs for characterizing the directionality of relationships in the diagram and in understanding confounding bias has been described in detail [21, 22]. For example, as depicted in Figure 5, if Y increased the probability of selection conditional on X and Z 1 , then the odds ratio e β SY would be assigned a positive value(> 1).…”
Section: Discussionmentioning
confidence: 99%
“…In a signed DAG, edges are marked with the direction (positive or negative) of the average effect for each pair of directly connected variables, conditional on other relevant variables. The use of signed DAGs for characterizing the directionality of relationships in the diagram and in understanding confounding bias has been described in detail [21, 22]. For example, as depicted in Figure 5, if Y increased the probability of selection conditional on X and Z 1 , then the odds ratio e β SY would be assigned a positive value(> 1).…”
Section: Discussionmentioning
confidence: 99%
“…Their approach requires both a whole DAG over all variables and the signs of all edges on each path between the two variables. VanderWeele and Tan (2012) propose an approach for propagation of bounds within the DAG framework, which requires a known DAG with edgespecific bounds. Rubin (2004) discusses how to combine the results from two randomized trials of anthrax vaccine on human volunteers and macaques, where the outcome of interest, survival when challenged with lethal doses of anthrax, is available only from macaques.…”
Section: Introductionmentioning
confidence: 99%