Skip to main content
Open Access Publications from the University of California

Confounding Equivalence in Causal Inference

  • Author(s): Pearl, Judea
  • Paz, Azaria
  • et al.

The paper provides a simple test for deciding, from a given causal diagram, whether two sets of variables have the same bias-reducing potential under adjustment. The test requires that one of the following two conditions holds: either (1) both sets are admissible (i.e., satisfy the back-door criterion) or (2) the Markov boundaries surrounding the manipulated variable(s) are identical in both sets. Applications to covariate selection and model testing are discussed.

Main Content
Current View