Confounding Equivalence in Causal Inference

03/15/2012
by   Judea Pearl, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset