DAGitty — draw and analyze causal diagrams

DAGitty is a browser-based environment for creating, editing, and analyzing causal diagrams (also known as directed acyclic graphs or causal Bayesian networks). The focus is on the use of causal diagrams for minimizing bias in empirical studies in epidemiology and other disciplines. For background information, see the "learn" page.

DAGitty is developed and maintained by Johannes Textor (Institute for Computing and Information Sciences, Radboud University, and Medical BioSciences department, Radboudumc, Nijmegen, The Netherlands).

Many algorithms implemented in DAGitty were developed in close collaboration with Maciej Liśkiewicz and Benito van der Zander, University of Lübeck, Germany (see literature references below).

DAGitty development happens on github. You can download all source code from there and also get involved.

How can I get help?

If you encounter any problems using DAGitty, or would like to have a certain feature implemented, write to me on Mastodon, post on github or write to "johannes {dot} textor {at} gmx {dot} de". Your feedback and bug reports are very welcome and contribute to making DAGitty a better experience for everyone. Past contributors are acknowledged in the manual.

Is it free?

Because the main purpose of DAGitty is facilitating the use of causal models in empirical studies, it is and will always be Free software (both "free as in beer" and "free as in speech"). You can copy, redistribute, and modify it under the terms of the GNU general public license. Enjoy!

DAGitty development has been sponsored by the Leeds Institute for Data Analytics and by the Deutsche Forschungsgemeinschaft (DFG), grant 273587939.

How can I cite DAGitty?

If you use DAGitty in your scientific work, please consider citing us:

Johannes Textor, Benito van der Zander, Mark K. Gilthorpe, Maciej Liskiewicz, George T.H. Ellison.
Robust causal inference using directed acyclic graphs: the R package 'dagitty'.
International Journal of Epidemiology 45(6):1887-1894, 2016.
PDF postprint

How can I learn more about how DAGitty works?

The algorithms used in DAGitty are described in more depth the following papers:

Johannes Textor, Maciej Liśkiewicz.
Adjustment Criteria in Causal Diagrams: An Algorithmic Perspective.
In Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011), pp. 681-688. AUAI press, 2011.

Benito van der Zander, Maciej Liśkiewicz, Johannes Textor.
Constructing Separators and Adjustment Sets in Ancestral Graphs.
In Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence (UAI 2014), pp. 907-916. AUAI Press, 2014.

Benito van der Zander, Johannes Textor, Maciej Liśkiewicz.
Efficiently Finding Conditional Instruments for Causal Inference.
In Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI 2015), pp. 3243-3249. AAAI Press, 2015.

Benito van der Zander, Maciej Liśkiewicz.
Separators and Adjustment Sets in Markov Equivalent DAGs.
In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI 2016), pp. 3315-3321. AAAI Press, 2016.

What other related software is out there?

There is currently quite a lot of activity in causal inference software. A few links:

• ggdag is a nice R package based on dagitty but tidyverse-compatible and with much better plotting functionality.
• shinydag is another GUI aimed at visualizing DAGs and exporting them in different publication-ready formats.
• TETRAD
• DAG program
• dagR
• daggle is a shiny app where you can practice the rules of DAG-based covariate selection.
• A JupyterLab extension to render dagitty models

Please contact me if you know of other programs that should be added to this list, or directly submit a pull request on github.