Estimation of Effects of Sequential Treatments by Reparameterizing Directed Acyclic Graphs

@inproceedings{Robins1997EstimationOE,
  title={Estimation of Effects of Sequential Treatments by Reparameterizing Directed Acyclic Graphs},
  author={James M. Robins and Larry A. Wasserman},
  booktitle={UAI},
  year={1997}
}
The standard way to parameterize the dis­ tributions represented by a directed acyclic graph is to insert a parametric family for the conditional distribution of each random vari­ able given its parents. We show that when one's goal is to test for or estimate an effect of a sequentially applied treatment, this natu­ ral parameterization has serious deficiencies. By reparameterizing the graph using struc­ tural nested models, these deficiencies can be avoided.