Short nitpick—lots of assumptions other than ignorability can work for identifying direct effects (there is more to life than covariate adjustment). In particular, if we can agree on the causal diagram, then all sorts of crazy identification can become possible.
Short nitpick—lots of assumptions other than ignorability can work for identifying direct effects (there is more to life than covariate adjustment). In particular, if we can agree on the causal diagram, then all sorts of crazy identification can become possible.