Evidence-appraisal glossary
Directed acyclic graph
A directed acyclic graph, or DAG, is a diagram of assumed causal relationships drawn as one-way arrows between variables with no feedback loops, used to decide which variables to adjust for. It makes causal assumptions explicit and shows which adjustments reduce bias and which create it.
Also called: DAG, causal diagram.
Researchers use DAGs to spot confounders worth controlling and colliders worth leaving alone, so an analysis estimates the effect it intends to. The graph encodes assumptions rather than proven facts, so a DAG built on mistaken beliefs gives confident but wrong guidance. It reveals the logical consequences of a causal story, and its usefulness depends on how well that story matches reality.
This is a plain-language methodology definition for reading research. It is general education, not medical advice.