Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A directed acyclic graph for interactions

Nilsson, Anton LU ; Bonander, Carl ; Strömberg, Ulf LU and Björk, Jonas LU (2021) In International Journal of Epidemiology 50(2). p.613-619
Abstract

BACKGROUND: Directed acyclic graphs (DAGs) are of great help when researchers try to understand the nature of causal relationships and the consequences of conditioning on different variables. One fundamental feature of causal relations that has not been incorporated into the standard DAG framework is interaction, i.e. when the effect of one variable (on a chosen scale) depends on the value that another variable is set to. In this paper, we propose a new type of DAG-the interaction DAG (IDAG), which can be used to understand this phenomenon. METHODS: The IDAG works like any DAG but instead of including a node for the outcome, it includes a node for a causal effect. We introduce concepts such as confounded interaction and total, direct... (More)

BACKGROUND: Directed acyclic graphs (DAGs) are of great help when researchers try to understand the nature of causal relationships and the consequences of conditioning on different variables. One fundamental feature of causal relations that has not been incorporated into the standard DAG framework is interaction, i.e. when the effect of one variable (on a chosen scale) depends on the value that another variable is set to. In this paper, we propose a new type of DAG-the interaction DAG (IDAG), which can be used to understand this phenomenon. METHODS: The IDAG works like any DAG but instead of including a node for the outcome, it includes a node for a causal effect. We introduce concepts such as confounded interaction and total, direct and indirect interaction, showing that these can be depicted in ways analogous to how similar concepts are depicted in standard DAGs. This also allows for conclusions on which treatment interactions to account for empirically. Moreover, since generalizability can be compromised in the presence of underlying interactions, the framework can be used to illustrate threats to generalizability and to identify variables to account for in order to make results valid for the target population. CONCLUSIONS: The IDAG allows for a both intuitive and stringent way of illustrating interactions. It helps to distinguish between causal and non-causal mechanisms behind effect variation. Conclusions about how to empirically estimate interactions can be drawn-as well as conclusions about how to achieve generalizability in contexts where interest lies in estimating an overall effect.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Causal inference, external validity, generalizability, interaction, internal validity, mediation
in
International Journal of Epidemiology
volume
50
issue
2
pages
7 pages
publisher
Oxford University Press
external identifiers
  • scopus:85107083327
  • pmid:33221880
ISSN
1464-3685
DOI
10.1093/ije/dyaa211
project
Nya statistiska ansatser för att bedöma betydelsen av selektion och variation i befolkningsbaserade kohort- och screeningundersökningar
language
English
LU publication?
yes
id
6c9ec74f-cd91-4892-b7a0-93278d165fa0
date added to LUP
2021-09-08 08:19:18
date last changed
2024-06-15 15:54:16
@article{6c9ec74f-cd91-4892-b7a0-93278d165fa0,
  abstract     = {{<p>BACKGROUND: Directed acyclic graphs (DAGs) are of great help when researchers try to understand the nature of causal relationships and the consequences of conditioning on different variables. One fundamental feature of causal relations that has not been incorporated into the standard DAG framework is interaction, i.e. when the effect of one variable (on a chosen scale) depends on the value that another variable is set to. In this paper, we propose a new type of DAG-the interaction DAG (IDAG), which can be used to understand this phenomenon. METHODS: The IDAG works like any DAG but instead of including a node for the outcome, it includes a node for a causal effect. We introduce concepts such as confounded interaction and total, direct and indirect interaction, showing that these can be depicted in ways analogous to how similar concepts are depicted in standard DAGs. This also allows for conclusions on which treatment interactions to account for empirically. Moreover, since generalizability can be compromised in the presence of underlying interactions, the framework can be used to illustrate threats to generalizability and to identify variables to account for in order to make results valid for the target population. CONCLUSIONS: The IDAG allows for a both intuitive and stringent way of illustrating interactions. It helps to distinguish between causal and non-causal mechanisms behind effect variation. Conclusions about how to empirically estimate interactions can be drawn-as well as conclusions about how to achieve generalizability in contexts where interest lies in estimating an overall effect.</p>}},
  author       = {{Nilsson, Anton and Bonander, Carl and Strömberg, Ulf and Björk, Jonas}},
  issn         = {{1464-3685}},
  keywords     = {{Causal inference; external validity; generalizability; interaction; internal validity; mediation}},
  language     = {{eng}},
  month        = {{05}},
  number       = {{2}},
  pages        = {{613--619}},
  publisher    = {{Oxford University Press}},
  series       = {{International Journal of Epidemiology}},
  title        = {{A directed acyclic graph for interactions}},
  url          = {{http://dx.doi.org/10.1093/ije/dyaa211}},
  doi          = {{10.1093/ije/dyaa211}},
  volume       = {{50}},
  year         = {{2021}},
}