- Conditional probability
the quotient of the joint probability of two events in the same space and the marginal probability of one of the events
- Confounding
association between two variables due to a third variable
- Consistency assumption
for a given individual, the observed outcome equals the potential outcome, as a function of intervention, when the intervention is set to the observed level
- Counterfactual reasoning
comparing potential outcomes of alternative interventions with observed outcomes in a thought experiment
- d-separation
variables
and 
are said to be 
-separated, if all paths from to are blocked. A path may be blocked by a set of variables 
, if the path contains at least one arrow-emitting variable that is in or if the path contains at least one collider that is not in S and has no descendent in . A collider is defined as a variable on a path such that the path enters and leaves via arrow heads. and are, therefore, -separated conditional on , if blocks all paths between and . X and Y are marginally independent when S contains the null set - Direct effect
the expected change in outcome in response to changing exposure while holding all other variables fixed
- Directed acyclic graph (DAG)
a graph in which nodes represent variables and arrows represent influence between the variables they connect without loops; an arrow drawn from variable
to variable represents a dependency of on , and no dependency of on