Learn about DAGs and DAGitty
DAGitty's functions are described in the
PDF manual. However, the manual provides only very little introduction to DAGs themselves.
My recommended resource for learning about them is the book
"Causal Inference in Statistics: A Primer"
by Pearl, Glymour and Jewell. The Primer also contains exercises, many of which can be solved
using DAGitty and the DAGitty R package. See
the R vignette for the Primer.
If you are just getting started with DAGitty and the manual
seems like a little much, check out
the DAGitty primer/cheat sheet.
It will get you started in using DAGitty to draw and evaluate causal diagrams.
Below you can find some other resources for learning about DAGs and DAGitty.
Interactive Tutorials and Examples
This is a growing list of interactive tutorials about DAGs that are built in DAGitty itself.
- Parents, children, ancestors, descendants ... If you are confused
by all the graph terminology,
here's our little game to learn
- What is a confounder? A mediator? A proxy confounder? These are
all concepts that can only be defined by invoking causal language.
Learn in our
tutorial on covariate roles how
to spot such variables in DAGs.
The article d-Separation Without
Tears, adapted from Judea Pearl's textbook
"Causality", explains the key concept of d-separation in
"Table II Fallacy" is a
nice idiom introduced by
Westreich and Greenland.
It refers to the problems with interpreting the
coefficients in a multiple regression model causally,
including the widespread belief that coefficients in
such models are "mutually adjusted". Learn
here how to
properly interpret coefficients in multiple regression
The Simpson Machine illustrates
which causal structures can lead to Simpson's paradox, and
that valid covariate adjustment sets cannot be found without
The Single-Door Criterion can be used to
identify structural parameters (direct effects) in structural
equation models, even when the model as a whole is not identifiable.
This short tutorial explains what the single-door criterion can,
and cannot, do.
Make your own example! If you know a little HTML
above. Read here how!
DAGitty video tutorials
Some nice people have gone through the effort to make tutorial videos about how to use
dagitty. They are mainly based on 2.x versions, but still worth checking out:
Tutorial (video only) by
University of Helsinki
Introduction Literature on DAGs