For a better experience, click the Compatibility Mode icon above to turn off Compatibility Mode, which is only for viewing older websites.

Introduction to Directed Acyclic Graphs (DAGs) for Causal Inference Training

Wednesday, February 26, 2020

10:00 AM-12:00 PM

The Dornsife School of Public Health's Urban Health Collaborative and Research Office present this training that provides an introduction to DAG.
DAGs are diagrams used to represent causal questions. They serve as a visual aid to summarize assumptions about causal and non-causal associations between a given exposure and an outcome. DAGs are used to identify variables that must be measured and controlled for in order to obtain unconfounded effect estimates.

At the end of the training session, participants should be able to:
  • Recognize the essential elements of a DAG
  • Identify a collider variable
  • Use d-separation criteria to condition models on a set of adequate confounders
  • Draw a DAG and identify a minimal sufficient adjustment set of confounders using DAGitty interactive tool
Pricila Mullachery, PhD, MPH, postdoctoral research fellow, Urban Health Collaborative; and Ione Avila-Palencia, PhD, MPH, postdoctoral research fellow, Urban Health Collaborative.
Please RSVP by February 20 by emailing and please indicate if you plan to bring a laptop with you or would like us to provide one.

Contact Information


Remind me about this event. Notify me if this event changes. Add this event to my personal calendar.


3600 Market Street, Room 709


  • Everyone