Discussion on ''Nonparanormal Adjusted Marginal Inference'' by Susanne Dandl and Torsten Hothorn

This discussion provides commentary on the paper by Susanne Dandl and Torsten Hothorn entitled "Nonparanormal Adjusted Marginal Inference". The authors propose a novel covariate-adjusted model that features an explicit formulation of the marginal treatment effect in clinical trials. In this discussion, I highlight the applicability of the proposed approach to Bayesian clinical trials. I argue that the proposed model facilitates meaningful specification of research hypotheses and Bayesian decision criteria, and demonstrate the utilities of the approach in the context of Bayesian design via a brief example.