Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Apr 5;30(4):153-162.
doi: 10.2188/jea.JE20190192. Epub 2020 Feb 1.

Causal Diagrams: Pitfalls and Tips

Etsuji Suzuki  1 , Tomohiro Shinozaki  2 , Eiji Yamamoto  3
Affiliations

Causal Diagrams: Pitfalls and Tips

Etsuji Suzuki et al. J Epidemiol. .

Abstract

Graphical models are useful tools in causal inference, and causal directed acyclic graphs (DAGs) are used extensively to determine the variables for which it is sufficient to control for confounding to estimate causal effects. We discuss the following ten pitfalls and tips that are easily overlooked when using DAGs: 1) Each node on DAGs corresponds to a random variable and not its realized values; 2) The presence or absence of arrows in DAGs corresponds to the presence or absence of individual causal effect in the population; 3) "Non-manipulable" variables and their arrows should be drawn with care; 4) It is preferable to draw DAGs for the total population, rather than for the exposed or unexposed groups; 5) DAGs are primarily useful to examine the presence of confounding in distribution in the notion of confounding in expectation; 6) Although DAGs provide qualitative differences of causal structures, they cannot describe details of how to adjust for confounding; 7) DAGs can be used to illustrate the consequences of matching and the appropriate handling of matched variables in cohort and case-control studies; 8) When explicitly accounting for temporal order in DAGs, it is necessary to use separate nodes for each timing; 9) In certain cases, DAGs with signed edges can be used in drawing conclusions about the direction of bias; and 10) DAGs can be (and should be) used to describe not only confounding bias but also other forms of bias. We also discuss recent developments of graphical models and their future directions.

Keywords: bias; causal inference; causality; confounding; directed acyclic graphs.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.. The relation between compatibility and faithfulness. See Section 2-2 and Box 1 for details.
Figure 2.
Figure 2.. Cohort matching on a confounder. We let A denote an exposure, Y denote an outcome, and C denote a confounder and matching variable. The variable S indicates whether an individual in the source population is selected for the matched study (1: selected, 0: not selected). See Section 2-7 for details.
Figure 3.
Figure 3.. Case-control matching on a confounder. We let A denote an exposure, Y denote an outcome, and C denote a confounder and matching variable. The variable S indicates whether an individual in the source population is selected for the matched study (1: selected, 0: not selected). See Section 2-7 for details.
Figure 4.
Figure 4.. DAG that properly illustrate the underlying causal structures, before conditioning on M. We let A denote a binary exposure (1 = received heart transplant, 0 = did not receive heart transplant) and Y denote a binary outcome (1 = deceased, 0 = did not decease) and M denote a binary covariate (1 = men, 0 = women). DAG, directed acyclic graph.
Figure 5.
Figure 5.. DAG that properly illustrate the underlying causal structures, after conditioning on M. We let A denote a binary exposure (1 = received heart transplant, 0 = did not receive heart transplant) and Y denote a binary outcome (1 = deceased, 0 = did not decease) and M denote a binary covariate (1 = men, 0 = women). DAG, directed acyclic graph.
Figure 6.
Figure 6.. DAG that does not properly illustrate the underlying causal structures. We let A denote a binary exposure (1 = received heart transplant, 0 = did not receive heart transplant) and Y denote a binary outcome (1 = deceased, 0 = did not decease) and M denote a binary covariate (1 = men, 0 = women). DAG, directed acyclic graph.
See this image and copyright information in PMC

Comment in

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Greenland S, Pearl J, Robins JM. Causal diagrams for epidemiologic research. Epidemiology. 1999;10:37–48. 10.1097/00001648-199901000-00008 - DOI - PubMed
    1. Pearl J. Causality: Models, Reasoning, and Inference. 2nd ed. New York, NY. Cambridge University Press; 2009.
    1. Glymour MM, Greenland S. Causal diagram. In: Rothman KJ, Greenland S, Lash TL, eds. Modern Epidemiology. 3rd ed. Philadelphia, PA: Lippincott Williams & Wilkins; 2008:183–209.
    1. Glymour MM. Using causal diagrams to understand common problems in social epidemiology. In: Oakes JM, Kaufman JS, eds. Methods in Social Epidemiology. 2nd ed. San Francisco, CA: Jossey-Bass; 2017:458–492.
    1. Hernán MA, Robins JM. Causal Inference: What If. Boca Raton, FL. Chapman & Hall/CRC; 2020.